© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 118750
    Prev
    Next
    INDEX
    Explanations

    Mun

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stringify
    -0.08
     Mojo
    -0.08
    _PUSH
    -0.06
     Yo
    -0.06
     @$
    -0.06
     calls
    -0.06
    ��
    -0.06
    icides
    -0.06
     Imagine
    -0.06
     moisture
    -0.06
    POSITIVE LOGITS
     Mun
    0.08
    usion
    0.07
     miễn
    0.07
    ROC
    0.06
     commit
    0.06
    fruit
    0.06
     furious
    0.06
     uzav
    0.06
    ерп
    0.06
    oise
    0.06
    Activations Density 0.004%

    No Known Activations