© 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. 19-RESID-POST-AA
    6. 127033
    Prev
    Next
    INDEX
    Explanations

    academic papers

    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
    =form
    -0.07
    >An
    -0.07
     toda
    -0.07
    datatype
    -0.07
     Jong
    -0.06
    491
    -0.06
      	
    -0.06
    >y
    -0.06
    Refer
    -0.06
    hyp
    -0.06
    POSITIVE LOGITS
    /format
    0.06
     Patriots
    0.06
     Volunteer
    0.06
     nackte
    0.06
     ترب
    0.06
     Freddie
    0.06
    (identifier
    0.06
     identifying
    0.06
     chủ
    0.06
    ipples
    0.06
    Activations Density 0.006%

    No Known Activations