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. 27-RESID-POST-AA
    6. 9986
    Prev
    Next
    INDEX
    Explanations

    rainfall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                                      
    -0.06
     ghế
    -0.06
    _CHANNELS
    -0.06
    撤
    -0.06
     کان
    -0.06
    eses
    -0.06
     Resource
    -0.06
                                                         
    -0.06
     Resources
    -0.06
     Histogram
    -0.06
    POSITIVE LOGITS
     geopol
    0.07
    áci
    0.06
    .checkbox
    0.06
    .hit
    0.06
     žal
    0.06
    rain
    0.06
    λι
    0.06
     cev
    0.06
     CGI
    0.06
    =".$
    0.06
    Activations Density 0.006%

    No Known Activations