© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 81238
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to communication and responses in various contexts

    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
    /tiny
    -0.08
    .removeListener
    -0.08
    álo
    -0.07
    _suite
    -0.07
    ¯u
    -0.07
    @brief
    -0.07
    ÅŁÄ±
    -0.07
    svc
    -0.07
     пÑĸдÑģ
    -0.07
    áli
    -0.07
    POSITIVE LOGITS
     met
    0.10
    irsch
    0.08
     ignored
    0.08
     fails
    0.08
     failed
    0.07
     fail
    0.07
     rejected
    0.07
    ignored
    0.07
     rejection
    0.07
     recipients
    0.06
    Activations Density 0.079%

    No Known Activations