© 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. 90830
    Prev
    Next
    INDEX
    Explanations

    recovery

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on words or word segments that denote recovery, reversal, or improvement of a medical or biological condition.

    oai_token-act-pair · o4-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
    uxe
    -0.06
    Cover
    -0.06
    Chicken
    -0.06
    ãy
    -0.06
     Permission
    -0.06
     Castro
    -0.06
     admissions
    -0.06
     Delivery
    -0.06
    گار
    -0.06
    IVERY
    -0.06
    POSITIVE LOGITS
     Stateless
    0.07
     ống
    0.07
     optimistic
    0.07
    /sub
    0.07
     regret
    0.06
    .quality
    0.06
    .Horizontal
    0.06
    .Features
    0.06
    (_('
    0.06
    _POL
    0.06
    Activations Density 0.033%

    No Known Activations