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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125083
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron is triggered by floating‐point numeric values (decimal measurements) in the experimental data tables.

    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
                   ↵
    -0.06
    ��
    -0.06
    pios
    -0.06
     Lazar
    -0.06
     finder
    -0.06
    rgan
    -0.06
     oran
    -0.06
    Hashtable
    -0.06
    ITICAL
    -0.06
     теор
    -0.06
    POSITIVE LOGITS
    .Result
    0.07
    .y
    0.07
    이는
    0.07
     BigInt
    0.07
     بلکه
    0.07
    (baseUrl
    0.06
    亦
    0.06
     prvním
    0.06
     emb
    0.06
    �
    0.06
    Activations Density 0.000%

    No Known Activations