© 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. 87530
    Prev
    Next
    INDEX
    Explanations

    specific song titles and lyrics

    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
    elta
    -0.07
    uffy
    -0.07
     è¡ĮæĶ¿
    -0.07
    аÑĢÑĩ
    -0.07
    ì°°
    -0.07
    esign
    -0.07
    (bs
    -0.07
    .ur
    -0.06
    oord
    -0.06
     springfox
    -0.06
    POSITIVE LOGITS
     latter
    0.06
     ’
    0.06
    683
    0.06
    953
    0.06
    lc
    0.06
    906
    0.06
    vid
    0.06
    earn
    0.06
    icit
    0.05
    lak
    0.05
    Activations Density 0.029%

    No Known Activations