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. 5-LLAMASCOPE-RES-131K
    6. 126326
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Shin" or related variations/names

    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
    oftware
    -0.07
    Rated
    -0.07
    aq
    -0.07
    oš
    -0.06
    hrad
    -0.06
    AsyncResult
    -0.06
    ãĥ¥
    -0.06
    æĦıè§ģ
    -0.06
    ÑģÑĤеÑĢ
    -0.06
    stroy
    -0.06
    POSITIVE LOGITS
    fulness
    0.07
    rib
    0.07
    685
    0.07
    inki
    0.07
    nton
    0.06
    anical
    0.06
     éĶ
    0.06
    ving
    0.06
    richt
    0.06
    ildren
    0.06
    Activations Density 0.003%

    No Known Activations