© 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. 125466
    Prev
    Next
    INDEX
    Explanations

    criteria and requirements for application 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
    akov
    -0.07
    odka
    -0.06
    alyzer
    -0.06
    reh
    -0.06
    ager
    -0.06
    loquent
    -0.06
     matter
    -0.06
    upp
    -0.06
    ало
    -0.06
     accreditation
    -0.06
    POSITIVE LOGITS
     competition
    0.08
     competitiveness
    0.08
     конкÑĥÑĢ
    0.07
    .selection
    0.07
    EDGE
    0.07
    ionage
    0.06
    competition
    0.06
     EDGE
    0.06
     Competition
    0.06
     Selection
    0.06
    Activations Density 0.007%

    No Known Activations