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. 43555
    Prev
    Next
    INDEX
    Explanations

    temporal phrases indicating specific times of day or deadlines

    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
    nero
    -0.07
    tsy
    -0.07
    ickle
    -0.07
    sty
    -0.06
    iena
    -0.06
    ngen
    -0.06
    floor
    -0.06
    iro
    -0.06
    ansen
    -0.06
    vero
    -0.06
    POSITIVE LOGITS
     into
    0.12
     on
    0.10
     this
    0.09
     afternoon
    0.09
     enough
    0.09
     that
    0.09
     yesterday
    0.08
     the
    0.08
     morning
    0.08
     onto
    0.08
    Activations Density 0.009%

    No Known Activations