© 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. 118855
    Prev
    Next
    INDEX
    Explanations

    concepts related to document management and manipulation in coding

    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
    ogie
    -0.07
    éĢĥ
    -0.07
    áºŃn
    -0.07
    endon
    -0.06
    ract
    -0.06
     Separ
    -0.06
    .fix
    -0.06
    ALLERY
    -0.06
    ainless
    -0.06
    ç¥ĸ
    -0.06
    POSITIVE LOGITS
     overwrite
    0.12
     existing
    0.12
     replace
    0.11
     old
    0.10
    existing
    0.10
    _replace
    0.10
     replaces
    0.10
    -existing
    0.10
     replacing
    0.10
     Existing
    0.10
    Activations Density 0.047%

    No Known Activations