© 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. 86746
    Prev
    Next
    INDEX
    Explanations

    syntax related to configuration files and programming structures

    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
    s
    -0.07
     =
    -0.06
    annotate
    -0.06
    620
    -0.06
     Holden
    -0.06
     antis
    -0.06
    suit
    -0.06
    -
    -0.05
     Insider
    -0.05
    =
    -0.05
    POSITIVE LOGITS
    عاÙĦ
    0.07
    üstü
    0.07
    ë§Į
    0.07
    _TAC
    0.07
    uria
    0.07
    lama
    0.07
    .Iter
    0.07
    uctor
    0.06
    itre
    0.06
    akov
    0.06
    Activations Density 0.000%

    No Known Activations