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. 96034
    Prev
    Next
    INDEX
    Explanations

    expressions of curiosity and inquisitiveness

    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
    out
    -0.08
    ese
    -0.07
    off
    -0.07
    alle
    -0.07
    hem
    -0.06
    aled
    -0.06
    ilder
    -0.06
    /post
    -0.06
    419
    -0.06
    ouch
    -0.06
    POSITIVE LOGITS
    ously
    0.08
    ë¡ľìļ´
    0.07
    icial
    0.07
    ستاÙĨ
    0.07
    rippling
    0.07
    ì¡
    0.07
    ä¸įåΰ
    0.07
    Ñģклад
    0.07
    ÐĶÐļ
    0.07
    plr
    0.06
    Activations Density 0.007%

    No Known Activations