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. 11-RESID-POST-AA
    6. 78311
    Prev
    Next
    INDEX
    Explanations

    }

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fact
    -0.07
    AIN
    -0.07
     lively
    -0.06
    LE
    -0.06
     ATT
    -0.06
     Ze
    -0.06
     Bailey
    -0.06
     centre
    -0.06
     Canter
    -0.06
    	position
    -0.06
    POSITIVE LOGITS
    culos
    0.08
     }
    0.08
    -hash
    0.08
     dışarı
    0.08
     στους
    0.07
    Swift
    0.07
    )((
    0.07
    屆
    0.07
     фер
    0.07
    ().'
    0.07
    Activations Density 0.058%

    No Known Activations