© 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. 17842
    Prev
    Next
    INDEX
    Explanations

    inquiries about identity or recognition

    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
    egas
    -0.06
     Delta
    -0.06
    568
    -0.05
    form
    -0.05
    uger
    -0.05
    ENUM
    -0.05
    gran
    -0.05
    strict
    -0.05
    obj
    -0.05
    539
    -0.05
    POSITIVE LOGITS
    Ah
    0.11
     Ah
    0.10
     oh
    0.10
     Oh
    0.10
    “Oh
    0.09
    oh
    0.09
    Oh
    0.09
    "Oh
    0.08
    artz
    0.08
     ah
    0.08
    Activations Density 0.026%

    No Known Activations