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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 21359
    Prev
    Next
    INDEX
    Explanations

    stuck

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     東
    -0.07
     içeren
    -0.06
     minWidth
    -0.06
     música
    -0.06
     zwar
    -0.06
    .SetActive
    -0.06
     通
    -0.06
    acellular
    -0.06
    .jet
    -0.06
     requestCode
    -0.06
    POSITIVE LOGITS
    ünchen
    0.08
     ⇒
    0.07
    货
    0.07
    contact
    0.07
    (ERROR
    0.06
    로부터
    0.06
    reece
    0.06
    �
    0.06
     možnosti
    0.06
    ствен
    0.06
    Activations Density 0.025%

    No Known Activations