© 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. 61161
    Prev
    Next
    INDEX
    Explanations

    numerical specifications related to technical or engineering contexts

    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
    ANGO
    -0.07
    stanbul
    -0.07
    deque
    -0.06
     uninitialized
    -0.06
    Reusable
    -0.06
    _chr
    -0.06
     abstract
    -0.06
    tember
    -0.06
    ilestone
    -0.06
    oner
    -0.06
    POSITIVE LOGITS
     manual
    0.06
     Wonderland
    0.06
    owy
    0.06
    ÃŃs
    0.06
    uder
    0.06
     Sport
    0.06
     Guard
    0.06
    uste
    0.06
     &
    0.06
    uche
    0.05
    Activations Density 0.000%

    No Known Activations