© 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. 87302
    Prev
    Next
    INDEX
    Explanations

    references to security

    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
    eya
    -0.07
    elda
    -0.07
    osa
    -0.07
    plet
    -0.07
    머
    -0.07
    pis
    -0.06
    rames
    -0.06
    ноз
    -0.06
    song
    -0.06
    è¾°
    -0.06
    POSITIVE LOGITS
    ContextHolder
    0.07
     clearance
    0.06
    bé
    0.06
     Clearance
    0.06
     Kara
    0.06
     blanket
    0.06
     conscious
    0.06
    ĶåĽŀ
    0.06
     Blank
    0.06
    /security
    0.06
    Activations Density 0.021%

    No Known Activations