© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94146
    Prev
    Next
    INDEX
    Explanations

    references to official documents and reporting frameworks

    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
    oine
    -0.07
    zac
    -0.07
    .advance
    -0.06
    kil
    -0.06
    æ¦
    -0.06
    anut
    -0.06
    ulfilled
    -0.06
    avax
    -0.06
    師
    -0.06
    adle
    -0.06
    POSITIVE LOGITS
    /cpp
    0.07
     filed
    0.07
     GA
    0.06
    /report
    0.06
    ách
    0.06
     Annual
    0.06
     materially
    0.06
     annual
    0.06
    opher
    0.06
     Jahres
    0.06
    Activations Density 0.002%

    No Known Activations