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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 57720
    Prev
    Next
    INDEX
    Explanations

    filler words

    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
     Ezra
    -0.07
     voyeur
    -0.06
     ​​
    -0.06
     :-)
    -0.06
    ович
    -0.06
    	Dictionary
    -0.06
    REFIX
    -0.06
     мест
    -0.06
    preced
    -0.06
     gente
    -0.06
    POSITIVE LOGITS
    θο
    0.07
    _ROUT
    0.07
    .Head
    0.07
    (COM
    0.07
    .logout
    0.07
     defects
    0.06
     COMM
    0.06
    TAIL
    0.06
     яб
    0.06
     monitoring
    0.06
    Activations Density 0.000%

    No Known Activations