© 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. 126937
    Prev
    Next
    INDEX
    Explanations

    sections and organization of a paper or document

    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
    iores
    -0.06
     Goose
    -0.06
    avatel
    -0.06
    ám
    -0.06
    amer
    -0.06
    olini
    -0.06
    isoft
    -0.06
    İS
    -0.06
    é¡į
    -0.06
    наÑĩ
    -0.06
    POSITIVE LOGITS
    ega
    0.07
    atomy
    0.06
    ="../../../
    0.06
    following
    0.06
    formace
    0.06
    sb
    0.06
    以ä¸ĭ
    0.06
     follows
    0.06
    οÏį
    0.06
     following
    0.06
    Activations Density 0.006%

    No Known Activations