© 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. 57219
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations related to variables and their relations

    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
    cai
    -0.06
    esini
    -0.06
     prof
    -0.06
    ình
    -0.06
    ipi
    -0.06
     Demp
    -0.06
    prof
    -0.06
       
    -0.06
     mau
    -0.06
     formal
    -0.06
    POSITIVE LOGITS
    borg
    0.06
    ourcem
    0.06
     alike
    0.06
     Pearce
    0.06
    esser
    0.06
     etc
    0.06
    etc
    0.06
     ragaz
    0.06
    andler
    0.06
    ataka
    0.06
    Activations Density 0.088%

    No Known Activations