© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18388
    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_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
     trợ
    -0.06
     sehr
    -0.06
     θέση
    -0.06
    bare
    -0.06
    睡
    -0.06
    уть
    -0.06
     wax
    -0.06
     Fired
    -0.06
     méd
    -0.06
     tup
    -0.06
    POSITIVE LOGITS
    (ListNode
    0.08
     chapters
    0.07
     elim
    0.07
    '',
    0.07
    εύ
    0.07
     toplam
    0.07
    _prior
    0.06
     gear
    0.06
    'im
    0.06
    ]')↵
    0.06
    Activations Density 0.008%

    No Known Activations