© 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. 55957
    Prev
    Next
    INDEX
    Explanations

    references to organizations, institutions, or studies related to scientific research and reports

    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
    orsi
    -0.09
    pw
    -0.07
    .EntityFramework
    -0.07
    imson
    -0.07
    thinkable
    -0.06
    OPY
    -0.06
     hect
    -0.06
    sÃŃ
    -0.06
    erialize
    -0.06
    ILES
    -0.06
    POSITIVE LOGITS
    bones
    0.07
    utom
    0.07
    rena
    0.07
    aky
    0.06
     dem
    0.06
    IRO
    0.06
    Ø·ÙĦ
    0.06
    per
    0.06
     gravity
    0.06
     unm
    0.06
    Activations Density 0.016%

    No Known Activations