© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126911
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty and evaluations of experiences

    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
    entar
    -0.07
    tainment
    -0.07
    _FF
    -0.07
    ÐĴÑĤ
    -0.06
    GuidId
    -0.06
    .toolbox
    -0.06
    ÏģÏī
    -0.06
    oug
    -0.06
    smarty
    -0.06
     fır
    -0.06
    POSITIVE LOGITS
     quality
    0.07
    963
    0.07
     Nich
    0.07
    Łèĥ½
    0.07
    aukee
    0.07
     promises
    0.06
     Rede
    0.06
     good
    0.06
    335
    0.06
    084
    0.06
    Activations Density 0.050%

    No Known Activations