© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 54755
    Prev
    Next
    INDEX
    Explanations

    and

    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
    犯
    -0.07
    }],
    -0.06
    terrain
    -0.06
    meldung
    -0.06
    _SUPPORT
    -0.06
    YK
    -0.06
     της
    -0.06
     М
    -0.06
                                                    ↵
    -0.06
    -G
    -0.06
    POSITIVE LOGITS
     зовніш
    0.07
     organize
    0.07
     estoy
    0.07
    aru
    0.06
    aths
    0.06
    nth
    0.06
    asers
    0.06
    ussy
    0.06
     جنوب
    0.06
     oasis
    0.06
    Activations Density 0.640%

    No Known Activations