© 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. 42282
    Prev
    Next
    INDEX
    Explanations

    instances of significant punctuation or formatting used to emphasize or categorize 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
     exc
    -0.07
    erra
    -0.06
     bank
    -0.05
    oints
    -0.05
    igmat
    -0.05
     firm
    -0.05
     paper
    -0.05
     cult
    -0.05
     natural
    -0.05
    _MD
    -0.05
    POSITIVE LOGITS
    iner
    0.10
    णन
    0.09
    873
    0.07
    853
    0.07
    918
    0.07
    iners
    0.07
    osg
    0.07
     quý
    0.07
    akan
    0.07
     olun
    0.07
    Activations Density 0.000%

    No Known Activations