© 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. 128070
    Prev
    Next
    INDEX
    Explanations

    currency amounts

    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
    作为
    -0.07
    änner
    -0.06
     untuk
    -0.06
    ā
    -0.06
    unk
    -0.06
     pomp
    -0.06
     чувств
    -0.06
    ламент
    -0.06
    _crc
    -0.06
    oment
    -0.06
    POSITIVE LOGITS
     Wrong
    0.07
     unaware
    0.07
     area
    0.07
    =g
    0.07
    	Request
    0.06
     ).
    0.06
     contrario
    0.06
    .LOC
    0.06
     ning
    0.06
    .CO
    0.06
    Activations Density 0.020%

    No Known Activations