© 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. 5407
    Prev
    Next
    INDEX
    Explanations

    phrases associated with viewing or accessing content

    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
     btw
    -0.11
     incident
    -0.10
     BT
    -0.10
     Incident
    -0.08
    BT
    -0.07
    incident
    -0.07
    hq
    -0.06
    zimmer
    -0.06
    maal
    -0.06
    lobber
    -0.06
    POSITIVE LOGITS
    ulet
    0.07
    ke
    0.06
    pk
    0.06
    inus
    0.06
     Dud
    0.06
     двоÑĢ
    0.06
    νη
    0.06
     metab
    0.06
     IBOutlet
    0.06
    ÑĢаÑħ
    0.06
    Activations Density 0.025%

    No Known Activations