© 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. 35074
    Prev
    Next
    INDEX
    Explanations

    Random snippets of information

    np_max-act · gemini-2.0-flash

    narratives about daily experiences and personal reflections.

    oai_token-act-pair · gpt-4o-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
     helmets
    -0.07
     çoğ
    -0.06
    Disposable
    -0.06
     pog
    -0.06
    .Requires
    -0.06
     Gobierno
    -0.06
     výj
    -0.06
    와
    -0.06
    	properties
    -0.06
    пис
    -0.06
    POSITIVE LOGITS
    ころ
    0.07
    gl
    0.07
    隔
    0.06
    тим
    0.06
     hr
    0.06
    metics
    0.06
     офі
    0.06
     amid
    0.06
    [color
    0.06
     않는
    0.06
    Activations Density 0.405%

    No Known Activations