© 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. 126098
    Prev
    Next
    INDEX
    Explanations

    verbs associated with attempts and efforts to achieve specific actions or outcomes

    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
    esar
    -0.07
    ittest
    -0.06
    aku
    -0.06
    isson
    -0.06
    etter
    -0.06
    isky
    -0.06
    dale
    -0.06
    chten
    -0.06
    392
    -0.06
    oya
    -0.06
    POSITIVE LOGITS
    oco
    0.07
    Gatt
    0.07
    rens
    0.07
    å°
    0.07
    ordon
    0.07
    _________________↵↵
    0.07
    ubbles
    0.07
    å°Ħ
    0.06
    еÑĢжав
    0.06
    ocre
    0.06
    Activations Density 0.024%

    No Known Activations