© 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 EvalsExportsAPI 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. 56157
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and formatting symbols

    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
    avras
    -0.07
    lef
    -0.07
    avl
    -0.07
    imus
    -0.07
    rites
    -0.07
    erson
    -0.07
    aylor
    -0.07
    éf
    -0.07
    ç§Ģ
    -0.06
    ÏĥÏĨ
    -0.06
    POSITIVE LOGITS
     E
    0.06
     Fog
    0.06
    opup
    0.06
    otty
    0.06
    rin
    0.06
    INGTON
    0.05
     Area
    0.05
    lobe
    0.05
    åij½
    0.05
    Ä°n
    0.05
    Activations Density 0.002%

    No Known Activations