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. 43569
    Prev
    Next
    INDEX
    Explanations

    instances of ownership or achievements

    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
     Sh
    -0.15
    Sh
    -0.14
     SH
    -0.12
    /Sh
    -0.12
    .Sh
    -0.12
     Ш
    -0.11
    -Sh
    -0.11
    _Sh
    -0.11
    _SH
    -0.10
    -sh
    -0.10
    POSITIVE LOGITS
    ish
    0.17
    ishes
    0.15
    ished
    0.14
    ISH
    0.14
    ship
    0.13
    ash
    0.13
    ishing
    0.12
    dish
    0.12
    lash
    0.12
    ishly
    0.12
    Activations Density 0.007%

    No Known Activations