© 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. 11-RESID-POST-AA
    6. 90626
    Prev
    Next
    INDEX
    Explanations

    .Resources

    np_max-act · gemini-2.0-flash

    The neuron activates on the “res”/“ResXResource…” tokens in XML resource‐file headers, i.e. it spots resource‐file metadata entries like `<resheader>` and related ResX reader/writer names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FF
    -0.08
    aft
    -0.06
     AH
    -0.06
     Cly
    -0.06
     alumno
    -0.05
     glasses
    -0.05
     conferences
    -0.05
     pollen
    -0.05
    -signed
    -0.05
    ngen
    -0.05
    POSITIVE LOGITS
    (rng
    0.07
    (detail
    0.07
     atlas
    0.07
     efect
    0.07
     carne
    0.07
    ifdef
    0.07
    (rest
    0.06
    ρεια
    0.06
    .getBean
    0.06
     dostal
    0.06
    Activations Density 0.001%

    No Known Activations