© 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. 17-LLAMASCOPE-RES-131K
    11. 87429
    Prev
    Next
    INDEX
    Explanations

    descriptions of performance and achievements in sports

    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
    ansa
    -0.09
    hend
    -0.08
    .pref
    -0.08
    tuk
    -0.07
    ensa
    -0.07
    858
    -0.07
    oft
    -0.07
    inel
    -0.07
    MBProgressHUD
    -0.07
    @ResponseBody
    -0.07
    POSITIVE LOGITS
     http
    0.07
     cheap
    0.06
     bar
    0.06
     rev
    0.06
     termin
    0.06
    WR
    0.06
    DBObject
    0.06
     Fuse
    0.05
    Ļ
    0.05
     SS
    0.05
    Activations Density 0.003%

    No Known Activations