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. 7-RESID-POST-AA
    6. 26286
    Prev
    Next
    INDEX
    Explanations

    "ission" suffix

    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
     weighed
    -0.07
     LIMIT
    -0.06
     Races
    -0.06
    acos
    -0.06
     wage
    -0.06
     vets
    -0.06
     barric
    -0.06
     bar
    -0.06
    _ABORT
    -0.06
     gep
    -0.06
    POSITIVE LOGITS
     faut
    0.06
    SCALL
    0.06
     factual
    0.06
     f
    0.06
     HACK
    0.06
    ,j
    0.06
    efe
    0.06
    ",$
    0.06
    hive
    0.06
    _PATTERN
    0.06
    Activations Density 0.006%

    No Known Activations