© 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. 15-LLAMASCOPE-RES-131K
    11. 62095
    Prev
    Next
    INDEX
    Explanations

    terms related to fan engagement and community involvement

    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
    ÑģÑĤвоÑĢ
    -0.06
    use
    -0.06
     Mastery
    -0.06
     starting
    -0.06
     revolution
    -0.06
    itan
    -0.06
     mentioned
    -0.05
    èĬĿ
    -0.05
     Cena
    -0.05
    mentioned
    -0.05
    POSITIVE LOGITS
    ï¸
    0.08
    ElementException
    0.08
    efa
    0.08
    aeda
    0.08
    omik
    0.07
    andon
    0.07
    xFFF
    0.07
     erotico
    0.07
    .IContainer
    0.07
    ASI
    0.07
    Activations Density 0.008%

    No Known Activations