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. 91117
    Prev
    Next
    INDEX
    Explanations

    ay

    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
    (station
    -0.08
    (storage
    -0.08
    Meta
    -0.07
    _profile
    -0.07
    St
    -0.07
    opa
    -0.07
    plates
    -0.06
     projection
    -0.06
     Inter
    -0.06
     mastur
    -0.06
    POSITIVE LOGITS
     vm
    0.07
     ausp
    0.07
    )));↵
    0.07
     없습니다
    0.06
     �
    0.06
    �
    0.06
     Dě
    0.06
     }),↵↵
    0.06
    atabases
    0.06
     Eğer
    0.06
    Activations Density 0.086%

    No Known Activations