© 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. 69703
    Prev
    Next
    INDEX
    Explanations

    phrases related to escape or relief from daily struggles

    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
    ideos
    -0.07
    blr
    -0.07
    ÑģиÑĤ
    -0.07
    hd
    -0.07
    iode
    -0.07
    rouch
    -0.06
    coles
    -0.06
     expressive
    -0.06
    lÃŃÄį
    -0.06
    _assets
    -0.06
    POSITIVE LOGITS
     usual
    0.07
     fare
    0.07
    enti
    0.07
     continuous
    0.07
    pel
    0.07
    usual
    0.07
     constant
    0.07
     otherwise
    0.07
    .Exception
    0.07
    CONST
    0.07
    Activations Density 0.010%

    No Known Activations