Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126501
    Prev
    Next
    INDEX
    Explanations

    locations, specifically the state of California

    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
    .react
    -0.07
    yang
    -0.07
    icha
    -0.07
    illet
    -0.07
     Erot
    -0.06
    ÑĸÑĩ
    -0.06
    unal
    -0.06
    ãĥĸãĥª
    -0.06
    igel
    -0.06
    stalk
    -0.06
    POSITIVE LOGITS
    cka
    0.07
     portable
    0.07
     rum
    0.06
    견
    0.06
    .pitch
    0.06
     *)((
    0.06
     Portable
    0.06
    è¡Ľ
    0.06
    PTY
    0.06
    aliases
    0.06
    Activations Density 0.000%

    No Known Activations