© 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. 3267
    Prev
    Next
    INDEX
    Explanations

    timestamped post information and metadata

    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
     Vz
    -0.06
     Mik
    -0.06
    akra
    -0.06
    arrera
    -0.06
    %^
    -0.06
     Von
    -0.06
    argin
    -0.06
    azar
    -0.06
    pare
    -0.05
    ikip
    -0.05
    POSITIVE LOGITS
     bibli
    0.08
    inoa
    0.07
    æݪ
    0.07
    _reading
    0.07
    libraries
    0.07
    èį·
    0.07
    etag
    0.07
    jedn
    0.07
    oir
    0.07
    reads
    0.07
    Activations Density 0.015%

    No Known Activations