© 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. 126245
    Prev
    Next
    INDEX
    Explanations

    recommendations for book series and their continuity

    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
    -language
    -0.06
    grave
    -0.06
    rag
    -0.06
    wor
    -0.06
    anova
    -0.06
    amac
    -0.06
    uckets
    -0.06
    _MPI
    -0.06
    ãĥ«ãĥĪ
    -0.05
    izard
    -0.05
    POSITIVE LOGITS
     series
    0.08
     Chronicle
    0.08
     order
    0.08
     recommended
    0.07
     ConnectionState
    0.07
    idir
    0.07
    'order
    0.07
     Missing
    0.07
    582
    0.07
    avenport
    0.07
    Activations Density 0.015%

    No Known Activations