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. 43723
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transformation or evolution

    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
    amiliar
    -0.06
    .previous
    -0.06
     ONLY
    -0.06
     favourable
    -0.06
    egrity
    -0.06
     Previous
    -0.06
     favorable
    -0.06
     safest
    -0.06
    оÑģÑĤÑĥп
    -0.06
    ainless
    -0.06
    POSITIVE LOGITS
     full
    0.18
     actual
    0.15
     fully
    0.15
     fuller
    0.14
     outright
    0.14
     bona
    0.13
    full
    0.13
    (full
    0.12
    -full
    0.12
     something
    0.12
    Activations Density 0.067%

    No Known Activations