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. 11-RESID-POST-AA
    6. 66018
    Prev
    Next
    INDEX
    Explanations

    on

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Containers
    -0.07
    달
    -0.07
     عوامل
    -0.07
     багатьох
    -0.06
     deterioration
    -0.06
     Damage
    -0.06
    ()">↵
    -0.06
     metam
    -0.06
    ,string
    -0.06
    -ever
    -0.06
    POSITIVE LOGITS
     Osc
    0.07
    pause
    0.07
    )?↵↵
    0.06
    	ss
    0.06
     Prov
    0.06
     quelque
    0.06
     powers
    0.06
    promise
    0.06
    .Comm
    0.06
    nev
    0.06
    Activations Density 0.008%

    No Known Activations