© 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. 125371
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial machinery or processes

    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
    urma
    -0.07
    eking
    -0.07
    ÄĻd
    -0.07
    dum
    -0.06
    OrFail
    -0.06
    @student
    -0.06
    omba
    -0.06
    ibraltar
    -0.06
    alsy
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
     Schw
    0.07
     floated
    0.06
    ERVED
    0.06
    깨
    0.06
    èĬĻ
    0.06
    973
    0.06
     Stub
    0.06
    isoft
    0.06
     Harden
    0.06
    .soft
    0.06
    Activations Density 0.004%

    No Known Activations