© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94700
    Prev
    Next
    INDEX
    Explanations

    a

    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
    /../
    -0.06
     kính
    -0.06
    /tmp
    -0.06
                                                    
    -0.06
     devam
    -0.06
    _book
    -0.06
    渡
    -0.06
    	freopen
    -0.06
    won
    -0.05
     Cool
    -0.05
    POSITIVE LOGITS
    a
    0.08
     supporting
    0.07
     Прот
    0.07
     authorized
    0.07
     ache
    0.07
    _A
    0.07
    ,A
    0.07
    -A
    0.07
    -term
    0.07
     apprentices
    0.07
    Activations Density 0.001%

    No Known Activations