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. 29085
    Prev
    Next
    INDEX
    Explanations

    negative contractions and phrases expressing disbelief or disagreement

    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
    orth
    -0.07
    izu
    -0.07
     niet
    -0.07
    æŀľ
    -0.07
    eil
    -0.07
    quip
    -0.06
    adu
    -0.06
    afen
    -0.06
    ama
    -0.06
    .actual
    -0.06
    POSITIVE LOGITS
     atleast
    0.07
    epad
    0.06
     eventually
    0.06
    endir
    0.06
     Gree
    0.06
    IRD
    0.06
     Cummings
    0.06
    Gre
    0.06
     Levy
    0.06
    imals
    0.06
    Activations Density 0.027%

    No Known Activations