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. 22326
    Prev
    Next
    INDEX
    Explanations

    Blog/forum posts

    np_max-act · gemini-2.0-flash

    instances where the speaker expresses personal low mood, depression, stress, or asks for emotional help or support.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    하면
    -0.06
     BSON
    -0.06
    课
    -0.06
     photographed
    -0.06
    �
    -0.06
    姉
    -0.06
    ский
    -0.06
    ้ำ
    -0.06
    يب
    -0.06
    ارب
    -0.06
    POSITIVE LOGITS
     pou
    0.07
    _ib
    0.07
     bew
    0.07
     vol
    0.07
    ワイト
    0.07
     σχ
    0.07
    (theta
    0.06
     negligent
    0.06
     indiv
    0.06
     wishing
    0.06
    Activations Density 0.024%

    No Known Activations