© 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. 15-LLAMASCOPE-RES-131K
    11. 61894
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and settings related to device management and performance

    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
    imler
    -0.08
    cies
    -0.07
    fts
    -0.07
    ewe
    -0.07
    adesh
    -0.07
    egen
    -0.07
    immel
    -0.07
    .fhir
    -0.07
    orical
    -0.07
    radient
    -0.07
    POSITIVE LOGITS
    -enabled
    0.09
     enabled
    0.07
     mode
    0.06
    -cap
    0.06
    enabled
    0.06
     und
    0.06
    -support
    0.06
     feature
    0.06
     turned
    0.06
    Mode
    0.06
    Activations Density 0.047%

    No Known Activations