© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123249
    Prev
    Next
    INDEX
    Explanations

    ging```

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grooming
    -0.07
    cheng
    -0.06
     bố
    -0.06
     nur
    -0.06
    (value
    -0.06
    �
    -0.06
    реп
    -0.06
    ="@
    -0.06
     Butterfly
    -0.06
     mote
    -0.06
    POSITIVE LOGITS
     dodge
    0.16
     Dodge
    0.08
    gers
    0.07
     Yong
    0.07
     QSql
    0.07
    รด
    0.07
     Politico
    0.07
     joined
    0.06
     province
    0.06
     grammar
    0.06
    Activations Density 0.004%

    No Known Activations