© 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. 126857
    Prev
    Next
    INDEX
    Explanations

    keywords related to surveys and polling

    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
    ozilla
    -0.07
     Moreno
    -0.07
    .toolbox
    -0.07
    @Resource
    -0.06
    rego
    -0.06
     Bishop
    -0.06
     PACKAGE
    -0.06
    cosa
    -0.06
     Bulk
    -0.06
     RectTransform
    -0.06
    POSITIVE LOGITS
    è¡
    0.07
    ime
    0.06
    åĬ¿
    0.06
    zan
    0.06
    formats
    0.06
    omp
    0.06
    ãĥ«ãĥķ
    0.06
    Others
    0.06
    ffen
    0.06
     tastes
    0.06
    Activations Density 0.000%

    No Known Activations