© 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. 29484
    Prev
    Next
    INDEX
    Explanations

    references to a book series and its installments

    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
    runs
    -0.07
     runs
    -0.06
    ائÙħØ©
    -0.06
     Frost
    -0.05
    _runs
    -0.05
     trot
    -0.05
    urr
    -0.05
     run
    -0.05
    سÙĦ
    -0.05
    .tech
    -0.05
    POSITIVE LOGITS
    isode
    0.10
    olume
    0.08
    orney
    0.08
    ripple
    0.08
    OptionsResolver
    0.08
    akest
    0.08
     volume
    0.07
    sav
    0.07
    obook
    0.07
    uess
    0.07
    Activations Density 0.033%

    No Known Activations