Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40368
    Prev
    Next
    INDEX
    Explanations

    references to figures or illustrations in the text

    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
    orum
    -0.07
    ieux
    -0.07
    coni
    -0.07
    chaft
    -0.06
    aju
    -0.06
    hausen
    -0.06
    asje
    -0.06
    dro
    -0.06
    idal
    -0.06
     {{{
    -0.06
    POSITIVE LOGITS
    šov
    0.08
    Äįel
    0.08
     podrob
    0.07
    ¦æĥħ
    0.07
    verbatim
    0.07
    ì͍
    0.07
    _________________↵↵
    0.07
     Morm
    0.07
    hart
    0.07
    ezier
    0.07
    Activations Density 0.009%

    No Known Activations