Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 94189
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash

    expressions of attraction and desire in the context of personal relationships.

    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
     PKK
    -0.06
     trace
    -0.06
     JSONArray
    -0.06
     merry
    -0.06
     jobject
    -0.06
     Gi
    -0.06
    _high
    -0.06
    Happy
    -0.05
     persuaded
    -0.05
     fence
    -0.05
    POSITIVE LOGITS
     YYSTACK
    0.07
    unfold
    0.07
    احث
    0.07
    jt
    0.07
     onların
    0.07
    	Add
    0.07
    ones
    0.06
     Из
    0.06
     lao
    0.06
     stealth
    0.06
    Activations Density 0.077%

    No Known Activations