© 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. 3425
    Prev
    Next
    INDEX
    Explanations

    game mechanics and character abilities

    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
    alon
    -0.09
    æĮij
    -0.07
    RelativeTo
    -0.07
    alette
    -0.07
    ssp
    -0.07
    imler
    -0.07
    rch
    -0.07
    race
    -0.07
    ction
    -0.06
    å¹
    -0.06
    POSITIVE LOGITS
     Marks
    0.06
     cáºŃn
    0.06
     Stanley
    0.06
     Bord
    0.06
     saw
    0.06
     Jury
    0.06
    atz
    0.06
     suck
    0.06
     traversal
    0.06
    ÙĪØ±Ø§Øª
    0.06
    Activations Density 0.008%

    No Known Activations