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. 76557
    Prev
    Next
    INDEX
    Explanations

    references to ingredient measurements and adjustments in recipes

    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
    asca
    -0.07
    ëį°
    -0.07
    ysa
    -0.07
    arat
    -0.07
    	fi
    -0.07
    amina
    -0.07
    .ua
    -0.07
    Ñģклад
    -0.06
    .bz
    -0.06
    ieten
    -0.06
    POSITIVE LOGITS
     additional
    0.08
     extra
    0.07
     Kons
    0.07
     fluid
    0.06
    .extra
    0.06
     thêm
    0.06
    оÑĢон
    0.06
    /add
    0.06
    iew
    0.06
    essler
    0.06
    Activations Density 0.019%

    No Known Activations