© 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. 124727
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stuck" or phrases related to being trapped or unable to move

    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
    ipc
    -0.07
    bons
    -0.07
    isle
    -0.06
    coni
    -0.06
    icontrol
    -0.06
    ime
    -0.06
    gos
    -0.06
    asher
    -0.06
    ibre
    -0.06
    Abs
    -0.06
    POSITIVE LOGITS
     forever
    0.07
    uation
    0.07
    esse
    0.07
    ETCH
    0.06
    çIJ
    0.06
     Cout
    0.06
    overflow
    0.06
    NESS
    0.06
     sÃłng
    0.06
    ness
    0.06
    Activations Density 0.007%

    No Known Activations