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. 11-RESID-POST-AA
    6. 74895
    Prev
    Next
    INDEX
    Explanations

    sanctions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scant
    -0.07
     Hubbard
    -0.07
     poetic
    -0.06
     メ
    -0.06
     najle
    -0.06
     jumping
    -0.06
    ��
    -0.06
     pad
    -0.06
    #include
    -0.06
    ersonic
    -0.06
    POSITIVE LOGITS
    BaseContext
    0.07
     exterior
    0.07
    gebn
    0.07
     semi
    0.07
     cara
    0.06
     автомати
    0.06
    andExpect
    0.06
    GORITHM
    0.06
    ollipop
    0.06
     flyer
    0.06
    Activations Density 0.074%

    No Known Activations