© 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. 5088
    Prev
    Next
    INDEX
    Explanations

    the presence of the forward slash character

    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
    isha
    -0.08
    .setPrototypeOf
    -0.07
    ocked
    -0.07
    ĩ
    -0.07
    zilla
    -0.07
    isman
    -0.07
    ãĥĩãĥ«
    -0.07
    igo
    -0.07
    mut
    -0.07
    beer
    -0.07
    POSITIVE LOGITS
    oupon
    0.07
    CSI
    0.06
    otas
    0.06
    ern
    0.06
    uren
    0.06
    .cms
    0.05
    otherwise
    0.05
    ros
    0.05
     sift
    0.05
     Estr
    0.05
    Activations Density 0.000%

    No Known Activations