© 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. 129105
    Prev
    Next
    INDEX
    Explanations

    references to legal precedents and court rulings

    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
    airo
    -0.06
     d
    -0.06
     etc
    -0.06
    vi
    -0.06
    Ñİ
    -0.06
    ulu
    -0.06
     Rated
    -0.05
    bu
    -0.05
    chaft
    -0.05
    Äįi
    -0.05
    POSITIVE LOGITS
     holdings
    0.07
    erox
    0.07
    panion
    0.07
    PackageManager
    0.07
    sq
    0.07
    anj
    0.07
    sj
    0.07
     ÑģпÑĢав
    0.07
     stare
    0.07
    ìĽħ
    0.07
    Activations Density 0.047%

    No Known Activations