© 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. 30590
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to membership status and rewards programs

    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
    otu
    -0.06
    imenti
    -0.06
    (s
    -0.06
    eah
    -0.05
    ernen
    -0.05
     Cosby
    -0.05
    ê°¤
    -0.05
    ISCO
    -0.05
     de
    -0.05
    olicit
    -0.05
    POSITIVE LOGITS
     level
    0.13
    -level
    0.13
    level
    0.12
    ê¸ī
    0.12
     düzey
    0.10
    级
    0.10
    ç´ļ
    0.10
    -minus
    0.09
     nivel
    0.09
    _level
    0.09
    Activations Density 0.062%

    No Known Activations