© 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. 30199
    Prev
    Next
    INDEX
    Explanations

    conversational phrases related to leaving or taking action

    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
     relaxed
    -0.06
    Wunused
    -0.06
    oli
    -0.06
    rawtypes
    -0.05
    enson
    -0.05
    оли
    -0.05
     Relax
    -0.05
     spot
    -0.05
    seau
    -0.05
     relaxation
    -0.05
    POSITIVE LOGITS
    939
    0.08
    \xff
    0.07
    ALES
    0.07
    ailer
    0.07
    VENTORY
    0.07
    åİ»äºĨ
    0.07
    <?↵
    0.07
     now
    0.07
    ales
    0.07
    _mk
    0.06
    Activations Density 0.016%

    No Known Activations