© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82853
    Prev
    Next
    INDEX
    Explanations

    phrases related to the reliability and guarantees associated with information or products

    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
    roup
    -0.06
    qed
    -0.06
     far
    -0.06
    oton
    -0.06
    磨
    -0.06
     deltas
    -0.06
    _visitor
    -0.06
    æ¥
    -0.06
    thes
    -0.05
    -пÑĢав
    -0.05
    POSITIVE LOGITS
    noDB
    0.07
    ź
    0.07
     Interstate
    0.07
     soud
    0.07
    /course
    0.07
     jadx
    0.07
    sert
    0.06
    anean
    0.06
     Fach
    0.06
    osate
    0.06
    Activations Density 0.001%

    No Known Activations