© 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. 15-LLAMASCOPE-RES-131K
    11. 61840
    Prev
    Next
    INDEX
    Explanations

    concepts related to security and management of sensitive or hazardous materials

    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
    QUE
    -0.07
    _STACK
    -0.06
     looph
    -0.06
    Ñĸж
    -0.06
    LOB
    -0.06
    DebugEnabled
    -0.06
    raj
    -0.06
    ÑģÑĤоÑı
    -0.06
    incr
    -0.06
    843
    -0.06
    POSITIVE LOGITS
     storage
    0.10
    -storage
    0.08
    storage
    0.08
     Storage
    0.08
     storing
    0.07
    curity
    0.07
     until
    0.07
    orage
    0.07
    iba
    0.07
    ibar
    0.07
    Activations Density 0.016%

    No Known Activations