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. 44435
    Prev
    Next
    INDEX
    Explanations

    terms related to progression and transformation

    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
    umption
    -0.08
    ÑĩаÑģÑĤ
    -0.07
    ervlet
    -0.07
    ãĤ¹ãĤ¿ãĥ¼
    -0.07
    antal
    -0.07
    vice
    -0.06
    actable
    -0.06
    etrofit
    -0.06
    Uvs
    -0.06
    æ¡IJ
    -0.06
    POSITIVE LOGITS
     into
    0.14
     organ
    0.11
    into
    0.10
     overtime
    0.09
     Into
    0.09
     its
    0.08
     to
    0.08
     from
    0.08
     over
    0.08
     morph
    0.08
    Activations Density 0.031%

    No Known Activations