© 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 EvalsExportsinterp-engineNEWAPI 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. 95124
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals, companies, and 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
    алеж
    -0.07
    .Reporting
    -0.07
    è¾
    -0.07
    aque
    -0.07
    æĨ¶
    -0.07
    å¿Ĩ
    -0.07
    าà¸ĩ
    -0.07
    umption
    -0.07
    ण
    -0.07
    iper
    -0.07
    POSITIVE LOGITS
    Portal
    0.07
    edback
    0.07
    fully
    0.07
    /OR
    0.06
    ingly
    0.06
    ted
    0.06
    zel
    0.06
    odon
    0.06
    /her
    0.06
     plain
    0.06
    Activations Density 0.183%

    No Known Activations