© 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. 15-LLAMASCOPE-RES-131K
    6. 62081
    Prev
    Next
    INDEX
    Explanations

    references to news sources or news-related content

    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
    ovel
    -0.06
     pud
    -0.06
    hes
    -0.06
     '
    -0.06
     steering
    -0.06
    onis
    -0.06
    oe
    -0.06
    à¹Īาà¸ĩà¸ģ
    -0.06
    sville
    -0.06
    essed
    -0.06
    POSITIVE LOGITS
    asca
    0.08
     ^{°}
    0.08
    elijk
    0.07
    linkplain
    0.07
    _exempt
    0.07
    arges
    0.07
    æ¡Ī
    0.07
     konkrét
    0.07
    /goto
    0.07
    bens
    0.07
    Activations Density 0.000%

    No Known Activations