Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95877
    Prev
    Next
    INDEX
    Explanations

    references to black-and-white imagery or photography

    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
    å·ŀ
    -0.07
    stag
    -0.06
    lez
    -0.06
    ,ID
    -0.06
     Gad
    -0.06
    ÑĢеÑĤ
    -0.06
     Painter
    -0.06
    λ
    -0.05
    amu
    -0.05
    @update
    -0.05
    POSITIVE LOGITS
    _VERSION
    0.08
    esson
    0.07
    Ä±ÅŁÄ±k
    0.07
    URA
    0.07
    gesi
    0.07
    URATION
    0.07
    иÑĨин
    0.07
    /raw
    0.07
     VERSION
    0.07
    ë©ĺ
    0.07
    Activations Density 0.004%

    No Known Activations