© 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. 9-LLAMASCOPE-RES-131K
    11. 95577
    Prev
    Next
    INDEX
    Explanations

    terms related to hearing and vision impairments

    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
    atham
    -0.08
    usto
    -0.08
     Rosenstein
    -0.07
    Ya
    -0.07
    æ´¾
    -0.07
    eturn
    -0.07
    viso
    -0.06
    ORA
    -0.06
    ora
    -0.06
    pond
    -0.06
    POSITIVE LOGITS
    βά
    0.06
     Microsystems
    0.06
    STALL
    0.06
    imm
    0.06
     imm
    0.06
    ening
    0.06
    DCALL
    0.06
    erez
    0.06
    /Foundation
    0.06
    ìĤ
    0.06
    Activations Density 0.002%

    No Known Activations