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. 3-RESID-POST-AA
    6. 122540
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ngo
    -0.06
    -town
    -0.06
     ih
    -0.06
     transpose
    -0.06
     جی
    -0.06
    εί
    -0.06
    erties
    -0.06
    ρχ
    -0.06
     norm
    -0.06
     bảo
    -0.06
    POSITIVE LOGITS
     Drug
    0.07
     Strat
    0.07
     oxidation
    0.07
     Artists
    0.07
     Overall
    0.06
    所以
    0.06
    製作
    0.06
    07
    0.06
    08
    0.06
    WithError
    0.06
    Activations Density 0.006%

    No Known Activations