© 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. 125535
    Prev
    Next
    INDEX
    Explanations

    instructions that describe adding or placing ingredients in a recipe

    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
    WRAPPER
    -0.07
     ÙħÛĮÙĦادÛĮ
    -0.07
    lite
    -0.06
    iless
    -0.06
    ä»ĺãģį
    -0.06
    .setResult
    -0.06
    bourne
    -0.06
    ilot
    -0.06
    _detach
    -0.06
     вк
    -0.06
    POSITIVE LOGITS
    entions
    0.06
    pressions
    0.06
    ¯¯¯¯
    0.06
    itsu
    0.06
    меÑĤÑĮ
    0.06
    rench
    0.06
    /downloads
    0.06
    WD
    0.06
     FCC
    0.05
     empty
    0.05
    Activations Density 0.025%

    No Known Activations