© 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 (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 10876
    Prev
    Next
    INDEX
    Explanations

    Formal writing/structure

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =j
    -0.07
     Ta
    -0.07
    fecha
    -0.07
     MOT
    -0.07
     Tax
    -0.07
    			↵
    -0.07
    _PUR
    -0.07
     Mei
    -0.06
    .he
    -0.06
    				↵
    -0.06
    POSITIVE LOGITS
     flags
    0.07
    っていた
    0.06
    獎
    0.06
    -clock
    0.06
     ObjectId
    0.06
     JsonResult
    0.06
     lors
    0.06
     injury
    0.06
    ripp
    0.06
    Expiration
    0.06
    Activations Density 0.000%

    No Known Activations