© 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. 17-LLAMASCOPE-RES-131K
    6. 83181
    Prev
    Next
    INDEX
    Explanations

    references to projects and initiatives

    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
     Dam
    -0.07
    innacle
    -0.07
    adier
    -0.07
    illow
    -0.07
    anker
    -0.07
    arking
    -0.07
    alles
    -0.07
    gua
    -0.07
    iker
    -0.07
     Newsp
    -0.06
    POSITIVE LOGITS
    yu
    0.07
     naturally
    0.06
    .tip
    0.06
    еÑĢо
    0.06
     Yu
    0.06
    Yu
    0.06
    landa
    0.06
    ÑĪев
    0.06
    icina
    0.06
     anzeigen
    0.06
    Activations Density 0.001%

    No Known Activations