© 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. 62063
    Prev
    Next
    INDEX
    Explanations

    phrases associated with decreased overall capacity or effectiveness

    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
    ,strlen
    -0.07
    ektor
    -0.07
    ãģĬãĤĬ
    -0.07
    ìĨ
    -0.07
    alla
    -0.07
    ãģ«ãģ¦
    -0.07
    acket
    -0.07
    иÑģк
    -0.07
    911
    -0.07
    bjerg
    -0.06
    POSITIVE LOGITS
    ãĥ£
    0.06
    amen
    0.06
    ahir
    0.06
     nues
    0.06
     judgement
    0.06
    seven
    0.06
     Sah
    0.06
     Notebook
    0.06
    олеÑĤ
    0.06
    mix
    0.06
    Activations Density 0.000%

    No Known Activations