© 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. 71398
    Prev
    Next
    INDEX
    Explanations

    mentions of manuscripts and related materials

    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
    addtogroup
    -0.07
    hit
    -0.07
    rang
    -0.07
    ä¸ĸ
    -0.07
     Transparency
    -0.06
    essler
    -0.06
    hud
    -0.06
    reon
    -0.06
    519
    -0.06
    zin
    -0.06
    POSITIVE LOGITS
    oppable
    0.09
    oucher
    0.07
    edla
    0.07
    bare
    0.07
    Ñıк
    0.07
    ous
    0.07
    ural
    0.07
    ured
    0.07
    YSTEM
    0.07
    iyat
    0.07
    Activations Density 0.002%

    No Known Activations