Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43974
    Prev
    Next
    INDEX
    Explanations

    verbs indicating existence or state of being

    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
    armed
    -0.06
    /small
    -0.06
    ubu
    -0.06
    missible
    -0.06
    agi
    -0.06
    stm
    -0.06
    ptrdiff
    -0.06
     Useful
    -0.05
    asurable
    -0.05
    }č↵č↵č↵č↵
    -0.05
    POSITIVE LOGITS
     similar
    0.12
     dictated
    0.12
     changed
    0.12
     reminiscent
    0.10
     altered
    0.10
     different
    0.10
     identical
    0.10
     influenced
    0.09
    changed
    0.09
     unchanged
    0.09
    Activations Density 0.088%

    No Known Activations