© 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. 17-LLAMASCOPE-RES-131K
    11. 83294
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and matrix notations

    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
    uchar
    -0.06
    ment
    -0.06
    й
    -0.06
     (
    -0.06
    meni
    -0.05
    лÑı
    -0.05
    ~
    -0.05
    ourses
    -0.05
     conf
    -0.05
     bulk
    -0.05
    POSITIVE LOGITS
    .undefined
    0.08
    croft
    0.08
    CharacterSet
    0.08
    #af
    0.07
    ãĥ³ãĥĸ
    0.07
    лини
    0.07
    (-(
    0.07
    .INSTANCE
    0.07
    ãĢĶ
    0.07
    lesia
    0.07
    Activations Density 0.020%

    No Known Activations