© 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. 126009
    Prev
    Next
    INDEX
    Explanations

    key terms related to eligibility criteria and policies

    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
    ç³
    -0.06
    ãĥĨãĥ«
    -0.06
    Äįka
    -0.06
    нам
    -0.06
    mods
    -0.06
    ingen
    -0.06
     trapping
    -0.06
    .compat
    -0.06
    ragen
    -0.06
     dear
    -0.06
    POSITIVE LOGITS
    osc
    0.07
    .hasNext
    0.07
     runner
    0.06
     award
    0.06
     estate
    0.06
     lis
    0.06
    bye
    0.06
     runners
    0.06
    icast
    0.06
     hunt
    0.06
    Activations Density 0.000%

    No Known Activations