© 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. 71548
    Prev
    Next
    INDEX
    Explanations

    formatting and structure elements in documents

    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
    725
    -0.07
    Segoe
    -0.07
    enco
    -0.06
    .Multiline
    -0.06
    زÙħ
    -0.06
    amina
    -0.06
    ãĢij
    -0.06
    è¼Ķ
    -0.06
    stanbul
    -0.06
     espect
    -0.06
    POSITIVE LOGITS
    DRAM
    0.07
     sig
    0.07
    untu
    0.07
     Sig
    0.06
     OMIT
    0.06
    wort
    0.06
    akit
    0.06
    tae
    0.06
    lose
    0.06
     ex
    0.06
    Activations Density 0.002%

    No Known Activations