Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 31624
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _for
    -0.07
    廊
    -0.06
    仲
    -0.06
    cret
    -0.06
    .Exchange
    -0.06
    749
    -0.06
    Mc
    -0.06
    Up
    -0.05
    �
    -0.05
     Patton
    -0.05
    POSITIVE LOGITS
    .Experimental
    0.07
    itoris
    0.07
    мерик
    0.07
    essed
    0.07
     Ang
    0.07
    WithEmailAndPassword
    0.07
     человеч
    0.06
     cận
    0.06
     음
    0.06
    Creation
    0.06
    Activations Density 0.004%

    No Known Activations