© 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. 76941
    Prev
    Next
    INDEX
    Explanations

    elements related to academic authorship and citation metrics

    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
    hra
    -0.07
    ICC
    -0.07
    orer
    -0.06
    ÑĤап
    -0.06
    âm
    -0.06
    Ìī
    -0.06
    itemid
    -0.06
    omination
    -0.06
    orian
    -0.06
    arda
    -0.06
    POSITIVE LOGITS
     publications
    0.06
    adge
    0.06
    eÄį
    0.06
    ais
    0.06
     Publications
    0.06
     Pub
    0.06
    ocl
    0.06
    generator
    0.06
    clude
    0.06
     GUIStyle
    0.06
    Activations Density 0.001%

    No Known Activations