© 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. 104353
    Prev
    Next
    INDEX
    Explanations

    specific categories or classifications related to structure and organization within various contexts

    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
    ':''
    -0.11
    .scalablytyped
    -0.09
    менÑĪ
    -0.09
    åľ
    -0.08
    ",-
    -0.08
    .radioButton
    -0.08
    ï¼ģ↵↵
    -0.08
     &)
    -0.07
    &)
    -0.07
    @student
    -0.07
    POSITIVE LOGITS
    ,
    0.13
    -,
    0.11
    ãĢģ
    0.11
    ;
    0.10
     ãĢģ
    0.09
     (
    0.08
    ãĢįãĢĮ
    0.08
    0.08
    à¥ĭà¤Ĥ,
    0.08
     ,
    0.08
    Activations Density 0.582%

    No Known Activations