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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95768
    Prev
    Next
    INDEX
    Explanations

    actions or instructions related to physical manipulation or adjustments

    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
    666
    -0.07
    uš
    -0.07
    phem
    -0.06
    Äįen
    -0.06
    mach
    -0.06
    iche
    -0.06
    iny
    -0.06
    hai
    -0.06
    ix
    -0.06
    addon
    -0.06
    POSITIVE LOGITS
    898
    0.07
    ,[],
    0.07
     Kel
    0.06
     ÙģÙĤ
    0.06
    ismet
    0.06
    IRT
    0.06
     Bever
    0.06
    493
    0.06
    vrier
    0.06
    letcher
    0.06
    Activations Density 0.011%

    No Known Activations