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. 7-RESID-POST-AA
    6. 85975
    Prev
    Next
    INDEX
    Explanations

    routine

    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
     lesser
    -0.07
    ..
    -0.07
    /pkg
    -0.07
     wings
    -0.07
    _One
    -0.07
    _mux
    -0.06
     pourrait
    -0.06
    .and
    -0.06
     high
    -0.06
    	channel
    -0.06
    POSITIVE LOGITS
    terra
    0.06
    .MoveNext
    0.06
     Indianapolis
    0.06
     Lucia
    0.06
    Tahoma
    0.06
    propertyName
    0.06
     trhu
    0.06
     پخش
    0.06
    �
    0.06
     hiss
    0.06
    Activations Density 0.019%

    No Known Activations