© 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. 92054
    Prev
    Next
    INDEX
    Explanations

    instances of physical tension or being held in place

    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
    dü
    -0.07
     Lever
    -0.07
    .Reporting
    -0.06
    .inc
    -0.06
    215
    -0.06
    388
    -0.06
    .destroy
    -0.06
    ngth
    -0.06
    xl
    -0.06
    toi
    -0.06
    POSITIVE LOGITS
     stuck
    0.07
    VENTORY
    0.07
    anges
    0.06
    cret
    0.06
    uet
    0.06
    lue
    0.06
     wherever
    0.06
    tach
    0.06
     mid
    0.06
    èĪī
    0.06
    Activations Density 0.043%

    No Known Activations