© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 61749
    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_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
    ≤
    -0.06
     recip
    -0.06
     Romantic
    -0.06
    \<^
    -0.06
     zero
    -0.06
    629
    -0.06
    hear
    -0.06
     Inject
    -0.06
    ATORY
    -0.06
     Included
    -0.06
    POSITIVE LOGITS
    rad
    0.07
    (fullfile
    0.06
     dumpster
    0.06
    keley
    0.06
    ун
    0.06
    aren
    0.06
     обов
    0.06
    unders
    0.06
    Configs
    0.06
    =headers
    0.06
    Activations Density 0.004%

    No Known Activations