© 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. 29488
    Prev
    Next
    INDEX
    Explanations

    comparisons and analyses of various topics

    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
     Locke
    -0.07
    371
    -0.06
    odu
    -0.06
    itles
    -0.06
    ovan
    -0.06
    971
    -0.06
     Wien
    -0.06
    ieres
    -0.06
    Tp
    -0.06
    kre
    -0.05
    POSITIVE LOGITS
     against
    0.10
     Against
    0.09
     пÑĢоÑĤи
    0.08
    against
    0.08
    /***/
    0.08
    _again
    0.07
    Against
    0.07
    ılıç
    0.07
    _cmos
    0.07
     compares
    0.07
    Activations Density 0.067%

    No Known Activations