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. 19-RESID-POST-AA
    6. 53932
    Prev
    Next
    INDEX
    Explanations

    personal writing

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unravel
    -0.07
    844
    -0.07
    iasi
    -0.06
    êu
    -0.06
     expulsion
    -0.06
     shuffled
    -0.06
     unbearable
    -0.06
    ()=>
    -0.06
    criteria
    -0.06
     beating
    -0.06
    POSITIVE LOGITS
    Tv
    0.08
    γμα
    0.07
    .Mouse
    0.07
     destruction
    0.07
    agrant
    0.07
     PERF
    0.06
     Sega
    0.06
     Tah
    0.06
     gly
    0.06
    (recv
    0.06
    Activations Density 0.233%

    No Known Activations