Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29423
    Prev
    Next
    INDEX
    Explanations

    dates and specific episode information

    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
    otten
    -0.07
    ASP
    -0.06
    occo
    -0.06
    anya
    -0.06
    Ë
    -0.06
    :
    -0.06
    ichni
    -0.06
    uteur
    -0.06
     Bip
    -0.05
    construct
    -0.05
    POSITIVE LOGITS
    пов
    0.09
    _viewer
    0.07
    лиÑĨ
    0.07
     episode
    0.07
    skin
    0.07
    HQ
    0.07
    /rules
    0.07
     ÑĢазви
    0.07
    yyyyMMdd
    0.07
    Viewer
    0.07
    Activations Density 0.005%

    No Known Activations