© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71547
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements within the text

    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
    owan
    -0.06
     Ov
    -0.06
     column
    -0.06
    acs
    -0.06
    Äł
    -0.06
    rib
    -0.06
    tick
    -0.06
    ted
    -0.06
    ibs
    -0.06
    ecure
    -0.06
    POSITIVE LOGITS
    ATAB
    0.07
    ycl
    0.07
    ινε
    0.06
    ãĥ³ãĥĸ
    0.06
    è¡
    0.06
    ook
    0.06
    /archive
    0.06
    CHANT
    0.06
    .Orientation
    0.06
     quần
    0.06
    Activations Density 0.002%

    No Known Activations