Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 112083
    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_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
     Ấ
    -0.08
     Sharks
    -0.07
    anch
    -0.07
    �
    -0.06
    طقة
    -0.06
     tahun
    -0.06
    edeki
    -0.06
     como
    -0.06
    uiltin
    -0.06
     jezd
    -0.06
    POSITIVE LOGITS
     Clip
    0.07
    estimate
    0.07
     Entities
    0.07
     stu
    0.06
     생
    0.06
     Nb
    0.06
     BYU
    0.06
     münchen
    0.06
     Fits
    0.06
     misleading
    0.06
    Activations Density 0.029%

    No Known Activations