© 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. 96886
    Prev
    Next
    INDEX
    Explanations

    suffixes typically used in literary or academic contexts

    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
    oš
    -0.06
     Kun
    -0.06
     vmax
    -0.06
    osit
    -0.06
     wie
    -0.06
     die
    -0.05
     Sig
    -0.05
    ikan
    -0.05
    iest
    -0.05
     Cous
    -0.05
    POSITIVE LOGITS
    ìĦł
    0.08
     èij
    0.07
    iaux
    0.07
    alion
    0.07
    neau
    0.07
     GOODMAN
    0.07
    lec
    0.07
    :request
    0.07
    ichier
    0.07
    ÅĻÃŃm
    0.07
    Activations Density 0.002%

    No Known Activations