© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28919
    Prev
    Next
    INDEX
    Explanations

    content guidelines and rules related to posting comments

    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
     Concord
    -0.07
     sdl
    -0.07
     Seç
    -0.07
    GP
    -0.07
    ignum
    -0.06
    _choices
    -0.06
     Sanat
    -0.06
     bazen
    -0.06
    άκ
    -0.06
    è¦Ĩ
    -0.06
    POSITIVE LOGITS
     Cree
    0.07
     link
    0.06
    ickey
    0.06
     links
    0.06
     linker
    0.06
    edException
    0.06
     "
    0.06
     solic
    0.06
     copyrighted
    0.06
    esin
    0.06
    Activations Density 0.011%

    No Known Activations