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. 44248
    Prev
    Next
    INDEX
    Explanations

    references to voting and election processes

    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
    ness
    -0.09
    ly
    -0.08
    _suite
    -0.07
    ties
    -0.07
    suite
    -0.07
    _VOLT
    -0.07
    woke
    -0.07
    _voltage
    -0.07
    Voltage
    -0.07
    ty
    -0.06
    POSITIVE LOGITS
     cast
    0.15
     count
    0.13
     tally
    0.13
    cast
    0.13
     tall
    0.12
    -count
    0.12
    _cast
    0.11
     totals
    0.11
     counted
    0.10
     counts
    0.10
    Activations Density 0.016%

    No Known Activations