© 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. 119373
    Prev
    Next
    INDEX
    Explanations

    numerical values and units related to industrial products or 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
    atti
    -0.07
    egal
    -0.06
    cket
    -0.06
    onDelete
    -0.06
    çe
    -0.06
     onBind
    -0.06
     guild
    -0.06
    gem
    -0.06
    tright
    -0.06
    ipt
    -0.06
    POSITIVE LOGITS
     steel
    0.07
    kv
    0.07
    Fade
    0.06
     strength
    0.06
    anst
    0.06
     ÐľÐ°ÑĤ
    0.06
    iy
    0.06
    utch
    0.06
     overst
    0.06
    ï¼
    0.06
    Activations Density 0.001%

    No Known Activations