© 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 EvalsExportsAPI 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. 87516
    Prev
    Next
    INDEX
    Explanations

    phrases related to failure or inadequacy

    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
    ombat
    -0.07
    shal
    -0.07
     Raid
    -0.07
    terminal
    -0.06
    aget
    -0.06
    355
    -0.06
    pdev
    -0.06
    deaux
    -0.06
    precated
    -0.06
    dbg
    -0.06
    POSITIVE LOGITS
     f
    0.07
    Ĥæķ°
    0.07
     fi
    0.07
    á»ĩ
    0.07
    gy
    0.07
    gf
    0.06
    /*č↵
    0.06
    kin
    0.06
    'gc
    0.06
    inos
    0.06
    Activations Density 0.021%

    No Known Activations