© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119134
    Prev
    Next
    INDEX
    Explanations

    references to limitations or constraints 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
    estre
    -0.07
    rung
    -0.07
    adele
    -0.07
    hsi
    -0.07
    olle
    -0.07
    ardon
    -0.07
    hta
    -0.06
    Äįel
    -0.06
    velle
    -0.06
    .tem
    -0.06
    POSITIVE LOGITS
     accomplished
    0.08
     packed
    0.07
     maximum
    0.07
     pack
    0.07
     maxim
    0.07
     productivity
    0.07
    oad
    0.07
     accomplish
    0.07
    PACK
    0.06
     maximize
    0.06
    Activations Density 0.087%

    No Known Activations