© 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. 11-RESID-POST-AA
    6. 110355
    Prev
    Next
    INDEX
    Explanations

    Hugs and kisses (xo)

    np_max-act · gemini-2.0-flash

    The neuron detects affectionate sign‐off tokens or emoticon fragments (like “x”, “ox”, “o”, “hugs”, “♥”) used at the ends of posts.

    oai_token-act-pair · o4-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
     відкрит
    -0.07
     hatır
    -0.07
     Trek
    -0.07
    addGap
    -0.07
    client
    -0.07
     informations
    -0.07
    itm
    -0.07
     ті
    -0.06
     facial
    -0.06
    тар
    -0.06
    POSITIVE LOGITS
     opacity
    0.07
     pooling
    0.07
    �
    0.06
    ○
    0.06
     adhesive
    0.06
    Christ
    0.06
    ㅠㅠ
    0.06
    AJ
    0.06
     Guidance
    0.06
    _ord
    0.06
    Activations Density 0.008%

    No Known Activations