© 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. 15-LLAMASCOPE-RES-131K
    11. 87554
    Prev
    Next
    INDEX
    Explanations

    methods for combining file paths

    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
    çĵľ
    -0.07
    ¥
    -0.06
    ợ
    -0.06
    FIT
    -0.06
     traps
    -0.06
    .bd
    -0.06
     пÑĢиÑģÑĤÑĥп
    -0.06
    å¹
    -0.06
    /libs
    -0.06
     hacks
    -0.05
    POSITIVE LOGITS
    Ī
    0.06
    .stamp
    0.06
    askets
    0.06
    iverz
    0.06
     dots
    0.06
    (),'
    0.06
    abella
    0.06
     dot
    0.06
    ackbar
    0.06
    .gdx
    0.06
    Activations Density 0.001%

    No Known Activations