© 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. 7-RESID-POST-AA
    11. 5417
    Prev
    Next
    INDEX
    Explanations

    asking questions/participating

    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
     thrill
    -0.07
     Appeals
    -0.06
    Bitte
    -0.06
    _eg
    -0.06
     uzav
    -0.06
    μές
    -0.06
    OLUTE
    -0.06
     soutěže
    -0.06
    atti
    -0.06
    Equality
    -0.06
    POSITIVE LOGITS
    _RESOURCES
    0.07
    nictvím
    0.07
     quen
    0.06
     平
    0.06
    	res
    0.06
     sens
    0.06
    _regions
    0.06
    	Returns
    0.06
     delivering
    0.06
     Catalan
    0.06
    Activations Density 0.131%

    No Known Activations