© 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. 106910
    Prev
    Next
    INDEX
    Explanations

    terms associated with nanoscale materials and their applications

    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
    hazi
    -0.07
    etur
    -0.07
     gypsum
    -0.07
    apid
    -0.06
    omore
    -0.06
     prote
    -0.06
    ocial
    -0.06
    åĪ»
    -0.06
    onymous
    -0.06
     Zug
    -0.06
    POSITIVE LOGITS
    CNT
    0.08
     suspended
    0.07
     suspension
    0.07
    áÅĻ
    0.07
     Buck
    0.07
     DWC
    0.07
     suspend
    0.07
     susp
    0.07
    vÄĽt
    0.07
    ÑĥÑĪ
    0.07
    Activations Density 0.001%

    No Known Activations