© 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. 695
    Prev
    Next
    INDEX
    Explanations

    terms related to educational and service offerings, particularly in training and storage solutions

    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
    reds
    -0.06
     Cous
    -0.06
    ahat
    -0.06
     Quint
    -0.06
    æ
    -0.06
    ua
    -0.05
    æĤ
    -0.05
    weeney
    -0.05
    ův
    -0.05
     Viv
    -0.05
    POSITIVE LOGITS
    \Dependency
    0.08
    474
    0.07
     norge
    0.07
    JsonValue
    0.07
    Reusable
    0.07
    728
    0.07
    fono
    0.07
    697
    0.07
    è¡
    0.07
    inge
    0.07
    Activations Density 0.001%

    No Known Activations