© 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. 90221
    Prev
    Next
    INDEX
    Explanations

    references to government and organizational partnerships

    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
    hausen
    -0.07
    emas
    -0.07
     Skin
    -0.07
    .FC
    -0.06
    anes
    -0.06
     skin
    -0.06
    haus
    -0.06
    ilip
    -0.06
    nout
    -0.06
    oud
    -0.06
    POSITIVE LOGITS
     global
    0.17
     elsewhere
    0.15
    global
    0.14
     national
    0.13
     worldwide
    0.13
    -global
    0.13
     globals
    0.12
    åħ¨åĽ½
    0.12
     globally
    0.12
     nationwide
    0.12
    Activations Density 0.339%

    No Known Activations