© 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. 118893
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity vulnerabilities and breaches

    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
    -wide
    -0.06
    iyi
    -0.06
    èª
    -0.06
    .au
    -0.06
    <>
    -0.06
    azen
    -0.06
    ska
    -0.06
    TERN
    -0.06
    wide
    -0.06
    <>↵
    -0.06
    POSITIVE LOGITS
    Occurred
    0.09
    DataURL
    0.08
    $MESS
    0.08
    DCALL
    0.07
    _OCCURRED
    0.07
    /error
    0.07
    indr
    0.07
    êµ´
    0.07
     IonicModule
    0.07
    FRING
    0.07
    Activations Density 0.033%

    No Known Activations