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. 92773
    Prev
    Next
    INDEX
    Explanations

    semiconductor

    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
     Nat
    -0.07
    @endforeach
    -0.07
     
    -0.06
     Hakk
    -0.06
    mut
    -0.06
     VL
    -0.06
    Nat
    -0.06
     ott
    -0.06
    .Gen
    -0.06
     neu
    -0.06
    POSITIVE LOGITS
     semiconductor
    0.11
     Semiconductor
    0.09
    iconductor
    0.09
     confronted
    0.07
    oscope
    0.07
     undisclosed
    0.07
    فصل
    0.06
     incess
    0.06
    iaux
    0.06
    ради
    0.06
    Activations Density 0.008%

    No Known Activations