© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94559
    Prev
    Next
    INDEX
    Explanations

    characters or individuals demonstrating assertive or noticeable behavior

    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
    tep
    -0.08
    alama
    -0.07
     olsa
    -0.07
    anna
    -0.07
    ymi
    -0.07
    물
    -0.06
    æĽ¾
    -0.06
    achuset
    -0.06
    azÄĥ
    -0.06
    trys
    -0.06
    POSITIVE LOGITS
     instead
    0.09
    instead
    0.08
     Instead
    0.08
    Instead
    0.07
     simply
    0.07
    esor
    0.07
     persists
    0.07
    persist
    0.06
     obst
    0.06
    pers
    0.06
    Activations Density 0.032%

    No Known Activations