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. 95953
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and personal experiences

    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
    roker
    -0.07
    ANI
    -0.07
    att
    -0.07
    obl
    -0.07
    ath
    -0.06
    oggler
    -0.06
    imer
    -0.06
    帶
    -0.06
    AndGet
    -0.06
    ipsis
    -0.06
    POSITIVE LOGITS
    oret
    0.10
    oretical
    0.09
    yonel
    0.07
     therefore
    0.07
    omi
    0.07
    ازÙĦ
    0.07
    agine
    0.07
    /topics
    0.06
    icing
    0.06
    IIIK
    0.06
    Activations Density 0.288%

    No Known Activations