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. 7-RESID-POST-AA
    6. 4397
    Prev
    Next
    INDEX
    Explanations

    Common words

    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
    ,temp
    -0.07
    986
    -0.07
     coop
    -0.06
    _unset
    -0.06
    _lista
    -0.06
     collectively
    -0.06
     ArrayAdapter
    -0.06
    _OBS
    -0.06
    _flight
    -0.06
     broaden
    -0.06
    POSITIVE LOGITS
     tweeting
    0.08
     zo
    0.07
    ướng
    0.06
     cartoons
    0.06
    ín
    0.06
    _KeyPress
    0.06
    ีท
    0.06
     Mein
    0.06
    पर
    0.06
    碰
    0.06
    Activations Density 0.057%

    No Known Activations