© 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. 9-LLAMASCOPE-RES-131K
    11. 96768
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to leaving or escaping situations

    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
    zin
    -0.07
    ens
    -0.07
    rien
    -0.07
    ãĥ¼ãĤ¹
    -0.07
    ameda
    -0.06
    ENS
    -0.06
     zich
    -0.06
    ÏĨοÏģ
    -0.06
    Å¡il
    -0.06
    tg
    -0.06
    POSITIVE LOGITS
    erno
    0.06
    495
    0.06
    acas
    0.06
    istrovstvÃŃ
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
    osten
    0.06
    ascus
    0.06
    isch
    0.06
    chia
    0.06
    umd
    0.06
    Activations Density 0.005%

    No Known Activations