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. 112790
    Prev
    Next
    INDEX
    Explanations

    3D graphics code

    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
    icans
    -0.07
    će
    -0.07
    Jordan
    -0.07
     Algorithm
    -0.07
     Database
    -0.07
     Paren
    -0.07
    коп
    -0.07
    ocht
    -0.07
    _CREATED
    -0.07
    hist
    -0.06
    POSITIVE LOGITS
     Ζ
    0.06
     الرح
    0.06
    esz
    0.06
    FLT
    0.06
    	              
    0.05
    ��
    0.05
     doz
    0.05
    113
    0.05
    )&&
    0.05
    .IN
    0.05
    Activations Density 0.014%

    No Known Activations