© 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. 105973
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions or partnerships

    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
    .FontStyle
    -0.07
    adia
    -0.07
     autobi
    -0.07
    опÑĢи
    -0.06
    aight
    -0.06
    .getElements
    -0.06
    ì°¸
    -0.06
    ıf
    -0.06
    occan
    -0.06
    имв
    -0.06
    POSITIVE LOGITS
     version
    0.09
     versions
    0.08
    ote
    0.08
    orth
    0.07
    çīĪæľ¬
    0.07
    version
    0.07
     Version
    0.07
    -version
    0.07
     treating
    0.07
     rendering
    0.06
    Activations Density 0.051%

    No Known Activations