© 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. 31622
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    sentences where the speaker personally reports feeling sad, depressed, grieving, or otherwise emotionally distressed.

    oai_token-act-pair · gpt-5-miniTriggered 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
     نزد
    -0.07
     ад
    -0.07
     //(
    -0.07
     Length
    -0.06
    �
    -0.06
     квад
    -0.06
     divisor
    -0.06
     господар
    -0.06
    armor
    -0.06
    IPLE
    -0.06
    POSITIVE LOGITS
    JJ
    0.06
    .links
    0.06
     PUSH
    0.06
    ……」↵↵
    0.06
     diplomats
    0.06
    Reusable
    0.06
     Fridays
    0.06
     GA
    0.06
    jp
    0.05
     compet
    0.05
    Activations Density 0.085%

    No Known Activations