© 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. 15-LLAMASCOPE-RES-131K
    6. 103721
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or data in a structured format

    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
    dic
    -0.07
    ÑĢава
    -0.07
    ùa
    -0.07
    unks
    -0.07
     reduction
    -0.06
    omik
    -0.06
    zimmer
    -0.06
    gran
    -0.06
     Michele
    -0.06
    лиÑĪ
    -0.06
    POSITIVE LOGITS
    _dyn
    0.07
    Bloc
    0.06
    503
    0.06
    ulton
    0.06
    rica
    0.06
     blast
    0.06
    å¹¹ç·ļ
    0.06
    ãĥĮ
    0.06
    _LEG
    0.05
    /browse
    0.05
    Activations Density 0.000%

    No Known Activations