© 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. 15-LLAMASCOPE-RES-131K
    11. 887
    Prev
    Next
    INDEX
    Explanations

    elements related to navigation and chat interfaces

    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
    iday
    -0.09
    å¹²
    -0.07
    .Async
    -0.07
    erson
    -0.07
    ÑĪев
    -0.07
    ignal
    -0.06
     Rei
    -0.06
    leigh
    -0.06
    enek
    -0.06
    .Pow
    -0.06
    POSITIVE LOGITS
    ovah
    0.07
    ROWSER
    0.07
    oenix
    0.06
    ROL
    0.06
     Barth
    0.06
    uards
    0.06
    622
    0.06
     surf
    0.06
    ulkan
    0.06
    ÂłkW
    0.06
    Activations Density 0.017%

    No Known Activations