© 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. 76269
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character sequence for string delimiters

    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
    AZY
    -0.07
    uco
    -0.07
    ATAB
    -0.06
    dit
    -0.06
    asz
    -0.06
    oge
    -0.06
    idata
    -0.06
    adol
    -0.06
    ocz
    -0.06
    ucu
    -0.06
    POSITIVE LOGITS
    çļĦå¿ĥ
    0.07
    0.06
    omitempty
    0.06
    pard
    0.06
    718
    0.06
    velle
    0.06
    oda
    0.06
    ServletResponse
    0.06
     ActionTypes
    0.06
    aky
    0.06
    Activations Density 0.001%

    No Known Activations