© 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. 9-LLAMASCOPE-RES-131K
    11. 96987
    Prev
    Next
    INDEX
    Explanations

    technical terms related to chemical substances and materials

    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
    agher
    -0.07
    ,
    -0.06
    iko
    -0.06
    -
    -0.06
     and
    -0.06
    ols
    -0.06
    isma
    -0.06
     Toni
    -0.06
     time
    -0.06
     during
    -0.06
    POSITIVE LOGITS
    üçük
    0.08
    esModule
    0.08
    _deinit
    0.07
    _PUS
    0.07
    actionDate
    0.07
    ryfall
    0.07
    IEnumerator
    0.07
    åĺ´
    0.07
    ãĥ¼ãĥĨ
    0.07
    æļ
    0.07
    Activations Density 0.002%

    No Known Activations