© 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. 83947
    Prev
    Next
    INDEX
    Explanations

    references to outcomes or results related to collaboration and productivity

    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
    alance
    -0.08
    λÏİ
    -0.07
    itty
    -0.07
    ë²Į
    -0.07
    üstü
    -0.07
    ifo
    -0.07
    erin
    -0.07
     Äijặt
    -0.07
    uali
    -0.06
    .dep
    -0.06
    POSITIVE LOGITS
     Fields
    0.07
    -fields
    0.07
     fields
    0.07
    Fields
    0.07
     Herm
    0.07
    fields
    0.06
     tang
    0.06
    58
    0.06
    ACY
    0.06
    se
    0.06
    Activations Density 0.010%

    No Known Activations