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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95917
    Prev
    Next
    INDEX
    Explanations

    terms related to legal entities and governance

    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
    eldom
    -0.07
    .gameserver
    -0.07
    enou
    -0.07
     Sadd
    -0.07
    alchemy
    -0.07
    ẩm
    -0.06
     Erotische
    -0.06
     å¾Ĵ
    -0.06
     kla
    -0.06
    .TODO
    -0.06
    POSITIVE LOGITS
    imir
    0.06
    yster
    0.06
     Lv
    0.06
     limp
    0.06
    sel
    0.06
    enant
    0.05
     Prairie
    0.05
    ighter
    0.05
    worker
    0.05
     sav
    0.05
    Activations Density 0.003%

    No Known Activations