© 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 (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 40608
    Prev
    Next
    INDEX
    Explanations

    eating/drinking/potions

    np_max-act · gemini-2.0-flash

    narrative passages about magical or sci‑fi transformations—often triggered by ingesting something—and detailed descriptions of ensuing bodily changes, sometimes with fetishistic or sexual overtones.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Eighth
    -0.07
     permalink
    -0.06
     Instances
    -0.06
     Glasgow
    -0.06
    、三
    -0.06
    ct
    -0.06
    730
    -0.06
     leftist
    -0.06
     nf
    -0.06
     chứ
    -0.06
    POSITIVE LOGITS
     techno
    0.07
    _fm
    0.06
    .rel
    0.06
    weathermap
    0.06
    .vertx
    0.06
     Semiconductor
    0.06
     patron
    0.06
     ByteArrayInputStream
    0.06
    uggest
    0.06
    .setOutput
    0.06
    Activations Density 0.097%

    No Known Activations