Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128774
    Prev
    Next
    INDEX
    Explanations

    references to locations and directional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rina
    -0.07
    ixin
    -0.06
    ç¼
    -0.06
     Appalachian
    -0.06
    /stdc
    -0.06
    umbo
    -0.06
    ford
    -0.06
    esh
    -0.06
    Äįi
    -0.06
    .extension
    -0.06
    POSITIVE LOGITS
    tran
    0.07
     prom
    0.07
     banks
    0.07
     crawl
    0.06
    @stop
    0.06
    ATIC
    0.06
    orta
    0.06
    ẻ
    0.06
    ROWS
    0.06
    contro
    0.06
    Activations Density 0.011%

    No Known Activations