© 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. 80446
    Prev
    Next
    INDEX
    Explanations

    statements that convey advice or guidance

    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
     here
    -0.07
    ologia
    -0.06
    eldo
    -0.06
    irez
    -0.06
    usercontent
    -0.06
    izza
    -0.06
     motivo
    -0.05
     éĥ
    -0.05
    ATERIAL
    -0.05
     intra
    -0.05
    POSITIVE LOGITS
    abouts
    0.08
    èĢ
    0.07
    esen
    0.07
    inded
    0.07
    #Region
    0.07
    fon
    0.07
    bane
    0.07
    ÙĤÙī
    0.07
    ooter
    0.07
     scr
    0.07
    Activations Density 0.005%

    No Known Activations