© 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. 27034
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical 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
    ConverterFactory
    -0.07
    èŤ
    -0.06
    ozem
    -0.06
    oin
    -0.06
    oad
    -0.06
    ë³ij
    -0.06
    cai
    -0.06
    okies
    -0.06
    ardy
    -0.06
     cos
    -0.06
    POSITIVE LOGITS
    odash
    0.07
     Jac
    0.06
     gloves
    0.06
    ìĨ
    0.06
     Chang
    0.06
    abox
    0.06
    cherche
    0.06
     Hod
    0.06
    ad
    0.06
    elling
    0.06
    Activations Density 0.043%

    No Known Activations