© 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. 906
    Prev
    Next
    INDEX
    Explanations

    references to transportation and spatial arrangements

    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
    TexImage
    -0.07
    ancell
    -0.06
    buat
    -0.06
    brig
    -0.06
    anz
    -0.06
    pcodes
    -0.06
    rote
    -0.06
    uros
    -0.06
    amm
    -0.06
    UNDLE
    -0.06
    POSITIVE LOGITS
     paging
    0.07
    -office
    0.07
     corporate
    0.07
     office
    0.07
    ehler
    0.07
    ContentLoaded
    0.07
    quiz
    0.06
    piler
    0.06
    ilter
    0.06
     Corporate
    0.06
    Activations Density 0.004%

    No Known Activations