© 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. 120315
    Prev
    Next
    INDEX
    Explanations

    mentions of names, particularly variations of the name "Mel."

    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
    rous
    -0.08
    foot
    -0.08
     >č↵
    -0.07
    ød
    -0.06
    IBUTE
    -0.06
    sse
    -0.06
    geois
    -0.06
     Dtype
    -0.06
    jandro
    -0.06
    exels
    -0.06
    POSITIVE LOGITS
    bie
    0.09
    bert
    0.08
    anie
    0.06
    had
    0.06
    ona
    0.06
    manual
    0.06
    ning
    0.06
    lick
    0.06
    μί
    0.06
    uder
    0.06
    Activations Density 0.015%

    No Known Activations