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. 3-RESID-POST-AA
    6. 95028
    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rena
    -0.06
    ác
    -0.06
    tered
    -0.06
    (keys
    -0.06
    _iterations
    -0.06
    _sensor
    -0.06
    jon
    -0.05
      ↵
    -0.05
    Parameters
    -0.05
     آبی
    -0.05
    POSITIVE LOGITS
     digestive
    0.08
    atürk
    0.06
     Herbert
    0.06
    ]+\
    0.06
    لك
    0.06
    Star
    0.06
     Large
    0.06
    multi
    0.06
     frm
    0.06
    );//
    0.06
    Activations Density 0.079%

    No Known Activations