© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129185
    Prev
    Next
    INDEX
    Explanations

    actions related to evasion or maneuvering

    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
    arkin
    -0.09
    ismet
    -0.08
    unda
    -0.08
    arov
    -0.07
     Äijá»Ļt
    -0.07
    usercontent
    -0.07
    COOKIE
    -0.07
    eless
    -0.07
    à¥įतन
    -0.07
    icari
    -0.07
    POSITIVE LOGITS
     obstacles
    0.08
     obstacle
    0.08
    rej
    0.07
     rather
    0.07
    æİī
    0.07
     bullets
    0.06
     incoming
    0.06
     harm
    0.06
     ed
    0.06
     pitfalls
    0.06
    Activations Density 0.014%

    No Known Activations