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. 72982
    Prev
    Next
    INDEX
    Explanations

    educated

    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
     map
    -0.07
     ترتیب
    -0.07
    mb
    -0.07
     immune
    -0.07
     death
    -0.06
     MS
    -0.06
    _Sh
    -0.06
     Death
    -0.06
     hare
    -0.06
     censor
    -0.06
    POSITIVE LOGITS
     cultivation
    0.07
     здійснення
    0.06
    ิญ
    0.06
     karış
    0.06
    (INVOKE
    0.06
    考试
    0.06
    Dialogue
    0.06
    	NullCheck
    0.06
    bourne
    0.06
     teklif
    0.06
    Activations Density 0.001%

    No Known Activations