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. 15-RESID-POST-AA
    6. 75169
    Prev
    Next
    INDEX
    Explanations

    German

    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
    rhs
    -0.07
     Німеч
    -0.07
     zoo
    -0.07
    -${
    -0.06
    (length
    -0.06
    (observer
    -0.06
    acobian
    -0.06
    iale
    -0.06
     isSelected
    -0.06
     Stateless
    -0.06
    POSITIVE LOGITS
     towers
    0.07
    	RTCT
    0.07
     spawn
    0.06
     NSArray
    0.06
     shocked
    0.06
     �
    0.06
     순간
    0.06
     neces
    0.06
    AttributeName
    0.06
     squirrel
    0.06
    Activations Density 0.085%

    No Known Activations