© 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. 93600
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicle features and characteristics

    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
    HeaderCode
    -0.07
    maal
    -0.07
    èĻ«
    -0.07
    Ấ
    -0.07
    itu
    -0.07
    rez
    -0.07
    ControlEvents
    -0.07
     rezerv
    -0.07
    .tw
    -0.07
    عاÙĨ
    -0.07
    POSITIVE LOGITS
     placement
    0.13
     position
    0.10
     distance
    0.10
    ä½įç½®
    0.10
     Placement
    0.09
     placements
    0.09
     location
    0.09
    Placement
    0.09
     positions
    0.09
     Distance
    0.09
    Activations Density 0.099%

    No Known Activations