© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16151
    Prev
    Next
    INDEX
    Explanations

    references to software installation or usage instructions

    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
     chÃŃ
    -0.07
     Hlav
    -0.07
    643
    -0.06
     Vo
    -0.06
    807
    -0.06
    oders
    -0.06
    ãĥ³ãĤº
    -0.06
    [--
    -0.06
    enberg
    -0.06
     Sloan
    -0.06
    POSITIVE LOGITS
    ektor
    0.07
    yll
    0.06
    raquo
    0.06
    ataka
    0.06
    ÙģÙĤ
    0.06
    omen
    0.06
    ÄŁit
    0.06
     Judith
    0.06
    uell
    0.06
    渡
    0.06
    Activations Density 0.001%

    No Known Activations