© 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. 17-LLAMASCOPE-RES-131K
    11. 106393
    Prev
    Next
    INDEX
    Explanations

    locations and identifiers related to facilities and services

    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
    anel
    -0.07
    .calls
    -0.07
    umbed
    -0.07
    oland
    -0.07
    fty
    -0.07
    stag
    -0.07
    asma
    -0.06
    anja
    -0.06
    ein
    -0.06
    IRT
    -0.06
    POSITIVE LOGITS
    icode
    0.07
    ews
    0.07
    enci
    0.06
    Ĩ
    0.06
    ìĦ¼
    0.06
    ervers
    0.06
    Font
    0.06
    otos
    0.06
     like
    0.06
    OTO
    0.06
    Activations Density 0.013%

    No Known Activations