© 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. 78305
    Prev
    Next
    INDEX
    Explanations

    terms related to graphic art and design

    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
     à¹Ĩ
    -0.07
    ÑģÑı
    -0.07
    째
    -0.07
    ities
    -0.07
    loh
    -0.07
    otr
    -0.07
    ibar
    -0.07
    IPS
    -0.07
    fw
    -0.07
    combe
    -0.06
    POSITIVE LOGITS
    ically
    0.11
    COPE
    0.08
    ical
    0.08
    matic
    0.07
     poles
    0.07
    Ñīие
    0.07
    onical
    0.07
     erotique
    0.07
    wers
    0.07
    /video
    0.07
    Activations Density 0.019%

    No Known Activations