© 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. 126441
    Prev
    Next
    INDEX
    Explanations

    information about bookings and availability

    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
    bia
    -0.07
    /cop
    -0.07
    象
    -0.07
    ych
    -0.07
    #ab
    -0.07
     sims
    -0.07
    ROME
    -0.07
    VIRTUAL
    -0.07
    ìĦ
    -0.07
    親
    -0.07
    POSITIVE LOGITS
     others
    0.06
     someone
    0.06
     elsewhere
    0.06
    averse
    0.06
     somebody
    0.06
     reserve
    0.06
    alties
    0.06
     Someone
    0.06
    ç«ĭãģ¦
    0.06
    èħ¾
    0.05
    Activations Density 0.008%

    No Known Activations