© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74962
    Prev
    Next
    INDEX
    Explanations

    elements related to assessment or evaluation

    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
    ÅĻ
    -0.06
    /workspace
    -0.06
     often
    -0.06
     sometimes
    -0.06
    etti
    -0.06
     spared
    -0.06
     hur
    -0.06
    acular
    -0.05
    alam
    -0.05
    pron
    -0.05
    POSITIVE LOGITS
    inston
    0.07
    ï¼
    0.07
    cljs
    0.07
    ÑĩÑĥ
    0.07
    λη
    0.07
    HORT
    0.07
    >manual
    0.07
    виÑĩай
    0.07
    .getTransaction
    0.06
    ç§ģãģ®
    0.06
    Activations Density 0.000%

    No Known Activations