© 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 (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 75589
    Prev
    Next
    INDEX
    Explanations

    only

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antidad
    -0.07
    	AT
    -0.07
    @NoArgsConstructor
    -0.07
    .--
    -0.06
    /*----------------------------------------------------------------
    -0.06
    amo
    -0.06
    >").
    -0.06
    .jpeg
    -0.06
     國
    -0.06
     Logan
    -0.06
    POSITIVE LOGITS
    -reader
    0.08
     Begins
    0.06
     Problem
    0.06
     faculties
    0.06
     only
    0.06
    -single
    0.06
     kWh
    0.06
    props
    0.06
    ioms
    0.06
     ор
    0.06
    Activations Density 0.021%

    No Known Activations