© 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. 7-RESID-POST-AA
    11. 58357
    Prev
    Next
    INDEX
    Explanations

    Darwin

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تها
    -0.08
     provoc
    -0.07
    gewater
    -0.07
    代表
    -0.07
    μένο
    -0.07
    leme
    -0.07
     coherence
    -0.07
     Δημο
    -0.07
    ونت
    -0.06
     pseudo
    -0.06
    POSITIVE LOGITS
     Darwin
    0.11
    	It
    0.06
    darwin
    0.06
     detrimental
    0.06
    _S
    0.06
    exact
    0.06
    	save
    0.06
    distributed
    0.06
    _placeholder
    0.06
     ◎
    0.06
    Activations Density 0.003%

    No Known Activations