© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65385
    Prev
    Next
    INDEX
    Explanations

    avenous

    np_max-act · gemini-2.0-flash

    technical language related to offshore engineering and structural support systems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to mentions of intravenous drug administration (e.g. “intravenous,” “infusion,” “anesthetized,” “intravenously”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tobacco
    -0.08
     Labs
    -0.07
    osloven
    -0.07
    –
    -0.07
    orque
    -0.06
    keys
    -0.06
    ۱۹۴
    -0.06
    webpack
    -0.06
     prescribed
    -0.06
    ("-
    -0.06
    POSITIVE LOGITS
    Ether
    0.08
    expire
    0.06
     bibli
    0.06
    /{{$
    0.06
    oul
    0.06
     compassion
    0.06
     MediaQuery
    0.06
    Uploaded
    0.06
     Sent
    0.06
    خاص
    0.06
    Activations Density 0.365%

    No Known Activations