Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29276
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pepper" in various contexts

    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
    hf
    -0.07
    stab
    -0.07
     exile
    -0.07
    sing
    -0.07
    acre
    -0.07
    afen
    -0.07
    ìļ©
    -0.06
     hyper
    -0.06
    erne
    -0.06
    space
    -0.06
    POSITIVE LOGITS
    oni
    0.08
    ermint
    0.07
    iness
    0.07
    interop
    0.07
    ah
    0.07
    ohl
    0.07
    auce
    0.07
    mith
    0.06
    ings
    0.06
    /tcp
    0.06
    Activations Density 0.010%

    No Known Activations