© 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. 27482
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or positioning

    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
    eden
    -0.07
    reb
    -0.07
    onders
    -0.07
    ãĥŃãĥ¼
    -0.06
    aken
    -0.06
     }};↵
    -0.06
    engo
    -0.06
    аÑĤе
    -0.06
    ÙĨداÙĨ
    -0.06
    venta
    -0.06
    POSITIVE LOGITS
     WK
    0.06
    ervals
    0.06
    63
    0.06
    å¤
    0.06
    èŤ
    0.06
    XS
    0.06
    åĬ
    0.06
    еÑĢин
    0.06
    ERA
    0.06
     macros
    0.06
    Activations Density 0.020%

    No Known Activations