© 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. 118636
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and trends

    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
     tiener
    -0.07
    xdb
    -0.07
    reason
    -0.07
    عÙĬ
    -0.06
    flip
    -0.06
    wide
    -0.06
    ến
    -0.06
    견
    -0.06
    azole
    -0.06
    ilater
    -0.06
    POSITIVE LOGITS
    éĽĨä¸Ń
    0.12
     concentrated
    0.10
     located
    0.08
    located
    0.08
     mainly
    0.08
     mostly
    0.08
     Concent
    0.08
     táºŃp
    0.08
    mostly
    0.07
     оÑģновном
    0.07
    Activations Density 0.100%

    No Known Activations