© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106076
    Prev
    Next
    INDEX
    Explanations

    phrases indicating secretive or private interactions

    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
    getNum
    -0.07
    код
    -0.07
    odash
    -0.07
    monds
    -0.07
    ubits
    -0.07
    vsp
    -0.07
    rych
    -0.07
     rer
    -0.07
    Ïģια
    -0.07
     CAB
    -0.07
    POSITIVE LOGITS
     Hun
    0.06
     Em
    0.06
     ofType
    0.06
     Signs
    0.06
    enville
    0.05
    ç½²
    0.05
     Attributes
    0.05
    avic
    0.05
    onor
    0.05
    aunch
    0.05
    Activations Density 0.000%

    No Known Activations