© 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. 5-LLAMASCOPE-RES-131K
    11. 126477
    Prev
    Next
    INDEX
    Explanations

    ingredients and quantities in cooking instructions

    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
    Å¡il
    -0.07
     вообÑīе
    -0.07
    _CIPHER
    -0.07
    erken
    -0.07
    alis
    -0.07
    ROTO
    -0.06
     Valor
    -0.06
    ÑĪи
    -0.06
     Jury
    -0.06
     ÑĥÑĩаÑģÑĤи
    -0.06
    POSITIVE LOGITS
    524
    0.06
    maz
    0.06
    _namespace
    0.06
    .:
    0.06
     moments
    0.06
    guid
    0.06
    olk
    0.06
    aises
    0.05
    ole
    0.05
     Nut
    0.05
    Activations Density 0.215%

    No Known Activations