© 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. 69485
    Prev
    Next
    INDEX
    Explanations

    concepts related to pursuing and realizing dreams

    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
    esto
    -0.06
    виÑĤ
    -0.06
    .Orientation
    -0.06
    nero
    -0.06
    ats
    -0.06
    emo
    -0.06
     Flour
    -0.06
    INDER
    -0.06
     unw
    -0.06
     flour
    -0.06
    POSITIVE LOGITS
    ActionCode
    0.08
    諸
    0.07
    .motion
    0.07
     cazzo
    0.07
    arus
    0.06
     geile
    0.06
    _Internal
    0.06
    ukkit
    0.06
    EntryPoint
    0.06
    akter
    0.06
    Activations Density 0.010%

    No Known Activations