© 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. 56483
    Prev
    Next
    INDEX
    Explanations

    declarations of public classes and methods in programming code

    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
    ictim
    -0.07
     Khu
    -0.07
    redient
    -0.07
    lernen
    -0.06
    jÃŃ
    -0.06
    essler
    -0.06
    edback
    -0.06
    lesc
    -0.06
    ereco
    -0.06
    obile
    -0.06
    POSITIVE LOGITS
    ATAB
    0.08
     Broad
    0.07
    enta
    0.06
    PELL
    0.06
     Alexandre
    0.06
     broad
    0.06
    ENTA
    0.06
    strup
    0.06
    .datatables
    0.06
     PIT
    0.06
    Activations Density 0.003%

    No Known Activations