© 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. 129932
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron spikes on occurrences of the word “possible” (i.e. conditional questions asking if something is possible).

    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
    ecektir
    -0.07
    identity
    -0.07
    talk
    -0.07
     معمولا
    -0.07
     جریان
    -0.06
    omu
    -0.06
     assistant
    -0.06
     SME
    -0.06
     Table
    -0.06
    divider
    -0.06
    POSITIVE LOGITS
    filters
    0.06
     lattice
    0.06
    .cache
    0.06
     yeme
    0.06
    <
    0.06
     confidently
    0.06
    ệnh
    0.06
    IBUTE
    0.06
    "=>$
    0.06
     tylko
    0.06
    Activations Density 0.019%

    No Known Activations