© 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. 49752
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    terms and phrases related to software licensing and copyright.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    _z
    -0.08
     зг
    -0.07
    (one
    -0.07
     antib
    -0.07
     проз
    -0.06
    ційних
    -0.06
    다운
    -0.06
     ス
    -0.06
     blonde
    -0.06
     Wer
    -0.06
    POSITIVE LOGITS
     constituent
    0.06
    PAY
    0.06
     Lifecycle
    0.06
    usuario
    0.06
     splitter
    0.06
    (Color
    0.06
     Faster
    0.05
    iterations
    0.05
     feasible
    0.05
    back
    0.05
    Activations Density 0.012%

    No Known Activations