© 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. 125784
    Prev
    Next
    INDEX
    Explanations

    references to event timings or introductions

    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
    inger
    -0.07
    .enumer
    -0.07
    VRT
    -0.06
    Gratis
    -0.06
    ungan
    -0.06
    åĸľ
    -0.06
    _diag
    -0.06
    icros
    -0.06
    IW
    -0.06
    hurst
    -0.06
    POSITIVE LOGITS
     Merlin
    0.07
    ī
    0.06
    iled
    0.06
    eko
    0.06
    etim
    0.06
     Cap
    0.06
    ÌĢ
    0.06
    ÌĨ
    0.06
    ungalow
    0.06
    alar
    0.06
    Activations Density 0.000%

    No Known Activations