© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55774
    Prev
    Next
    INDEX
    Explanations

    numerical data related to academic performance

    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
    ritt
    -0.06
    oles
    -0.06
    ammers
    -0.06
    ATAL
    -0.06
    ogn
    -0.06
    óż
    -0.06
     injunction
    -0.06
     Moody
    -0.06
    bere
    -0.06
    gom
    -0.05
    POSITIVE LOGITS
    кÑĥÑĤ
    0.08
    boom
    0.07
    /errors
    0.07
    iegel
    0.07
    OfDay
    0.06
    -await
    0.06
    rens
    0.06
    aret
    0.06
    annel
    0.06
    ì§ľ
    0.06
    Activations Density 0.001%

    No Known Activations