© 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. 129037
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "Ap."

    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
    leston
    -0.08
    assen
    -0.07
    ledge
    -0.07
    hardt
    -0.07
    ainty
    -0.07
    lest
    -0.07
    eenth
    -0.07
    Viewport
    -0.07
     HOLDERS
    -0.06
    preter
    -0.06
    POSITIVE LOGITS
     Ap
    0.09
     ap
    0.09
    -ap
    0.07
    (ap
    0.07
    à¤łà¤¨
    0.07
    emann
    0.06
     dụng
    0.06
    rika
    0.06
    regon
    0.06
     cause
    0.06
    Activations Density 0.010%

    No Known Activations