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. 44153
    Prev
    Next
    INDEX
    Explanations

    references to formal academic titles or positions

    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
     Miz
    -0.07
    nt
    -0.07
    artin
    -0.06
    331
    -0.06
    ¹Ħ
    -0.06
     Z
    -0.06
    enthal
    -0.06
    haven
    -0.06
    tul
    -0.06
    _nt
    -0.06
    POSITIVE LOGITS
    z
    0.12
    zem
    0.12
    zew
    0.10
    zp
    0.10
    za
    0.10
    zs
    0.10
    zym
    0.09
    zon
    0.09
    zeÅĦ
    0.09
    zek
    0.08
    Activations Density 0.001%

    No Known Activations