© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to cost-effective options

    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
    ague
    -0.07
    quila
    -0.07
    xae
    -0.06
    zza
    -0.06
    imal
    -0.06
    ades
    -0.06
    amac
    -0.06
    punk
    -0.06
    ansen
    -0.06
    á»ĭnh
    -0.06
    POSITIVE LOGITS
    riers
    0.07
    986
    0.06
    447
    0.06
     ì¤Ģ
    0.06
     barg
    0.06
     dostat
    0.06
    _deinit
    0.06
    ogy
    0.06
    812
    0.06
    618
    0.05
    Activations Density 0.000%

    No Known Activations