© 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. 42043
    Prev
    Next
    INDEX
    Explanations

    elements related to identity and survival

    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
    ewis
    -0.08
    vem
    -0.07
    kea
    -0.07
    lobber
    -0.07
    ServletRequest
    -0.07
    ilip
    -0.07
    zzo
    -0.07
    xce
    -0.06
    istar
    -0.06
    عÙħاÙĦ
    -0.06
    POSITIVE LOGITS
     escape
    0.08
     fleeing
    0.07
     Neon
    0.07
     flee
    0.07
     fled
    0.07
     fug
    0.07
    éĢĥ
    0.07
     hunted
    0.07
     escaped
    0.06
     sanctuary
    0.06
    Activations Density 0.020%

    No Known Activations