© 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. 59168
    Prev
    Next
    INDEX
    Explanations

    themes related to fragility and sensitivity

    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
     Denied
    -0.07
    ainment
    -0.07
    uga
    -0.07
    iben
    -0.06
    gue
    -0.06
    errer
    -0.06
    stial
    -0.06
    hyth
    -0.06
    llum
    -0.06
    μιÏĥ
    -0.06
    POSITIVE LOGITS
     fragile
    0.24
     sensitive
    0.22
     delicate
    0.20
     sensitivity
    0.19
    -sensitive
    0.19
     frag
    0.18
    Sensitive
    0.17
    æķı
    0.17
     vulnerable
    0.16
     sensit
    0.16
    Activations Density 0.088%

    No Known Activations