© 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. 7-RESID-POST-AA
    6. 31007
    Prev
    Next
    INDEX
    Explanations

    production

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     países
    -0.07
    (xhr
    -0.06
    .air
    -0.06
     마
    -0.06
     colder
    -0.06
    @Repository
    -0.06
    _FUNC
    -0.06
    environment
    -0.06
    _gender
    -0.06
     fin
    -0.06
    POSITIVE LOGITS
    toa
    0.08
    _pll
    0.07
     dues
    0.07
    iding
    0.07
    }`;↵
    0.07
    ided
    0.06
     oblivious
    0.06
    î
    0.06
     candidacy
    0.06
     Jame
    0.06
    Activations Density 0.005%

    No Known Activations