© 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. 119246
    Prev
    Next
    INDEX
    Explanations

    references to community concerns and social issues

    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
    ÐIJÑĢÑħÑĸв
    -0.08
     (“
    -0.07
    impan
    -0.06
     ('
    -0.06
    ollo
    -0.06
    owl
    -0.06
     onCreateViewHolder
    -0.06
    uco
    -0.06
    -----------*/↵
    -0.06
    adesh
    -0.06
    POSITIVE LOGITS
     according
    0.14
    according
    0.11
     says
    0.10
     said
    0.10
    ,"
    0.10
     According
    0.10
    According
    0.10
    ",
    0.10
     selon
    0.09
    ](
    0.09
    Activations Density 0.457%

    No Known Activations