© 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. 55918
    Prev
    Next
    INDEX
    Explanations

    words indicating quantity or multiplicity

    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
     pad
    -0.07
     mest
    -0.07
    ÃŃrk
    -0.07
    -pad
    -0.07
    lamaz
    -0.07
    ci
    -0.06
    bol
    -0.06
    entin
    -0.06
     Lean
    -0.06
    387
    -0.06
    POSITIVE LOGITS
    yne
    0.07
    uvo
    0.07
    aviest
    0.07
    ãĢħ
    0.07
    ToMany
    0.06
    odo
    0.06
    uve
    0.06
    antz
    0.06
    allest
    0.06
     factorial
    0.06
    Activations Density 0.031%

    No Known Activations