© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79405
    Prev
    Next
    INDEX
    Explanations

    :

    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
     Cath
    -0.07
     hadn
    -0.06
     revived
    -0.06
     THERE
    -0.06
    ー
    -0.06
    	exp
    -0.06
     mænd
    -0.06
     gaps
    -0.06
    _WARNING
    -0.06
    DEC
    -0.06
    POSITIVE LOGITS
    .Actions
    0.08
     ActivityCompat
    0.07
    (call
    0.07
    unordered
    0.06
    광역시
    0.06
    .INTER
    0.06
    -major
    0.06
    ICIAL
    0.06
    alent
    0.06
     HttpSession
    0.06
    Activations Density 0.002%

    No Known Activations