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. 61056
    Prev
    Next
    INDEX
    Explanations

    references to chalk or related words

    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
    .metro
    -0.07
    .cent
    -0.06
    lies
    -0.06
    /start
    -0.06
    OLF
    -0.06
    ariat
    -0.06
    586
    -0.06
     macro
    -0.06
    ee
    -0.06
     風
    -0.06
    POSITIVE LOGITS
    board
    0.08
    BOARD
    0.07
    ulace
    0.07
    tember
    0.07
    stone
    0.07
    bones
    0.07
    anooga
    0.07
    DIRECTORY
    0.07
    paque
    0.07
    boards
    0.07
    Activations Density 0.003%

    No Known Activations