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. 19-RESID-POST-AA
    6. 30667
    Prev
    Next
    INDEX
    Explanations

    for

    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
     возраст
    -0.07
    ClassLoader
    -0.07
    ynamics
    -0.06
    遣
    -0.06
    Measurement
    -0.06
    руж
    -0.06
    iram
    -0.06
    eníze
    -0.06
    -slider
    -0.06
    PathVariable
    -0.06
    POSITIVE LOGITS
    		
    ↵		
    ↵
    0.07
     Handlers
    0.07
     Aud
    0.06
     INLINE
    0.06
     Twitch
    0.06
     projectile
    0.06
    .DataGridViewContentAlignment
    0.06
     Odd
    0.06
     chanting
    0.06
     Elis
    0.06
    Activations Density 0.030%

    No Known Activations