© 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. 1907
    Prev
    Next
    INDEX
    Explanations

    expressions related to memory and forgetting

    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
    _STRIP
    -0.07
    ropa
    -0.07
    _frontend
    -0.07
    hart
    -0.07
    hunt
    -0.07
    holder
    -0.07
    átka
    -0.06
    adele
    -0.06
    ãģķãĤī
    -0.06
    aments
    -0.06
    POSITIVE LOGITS
    fulness
    0.10
     altogether
    0.07
     forget
    0.07
    ting
    0.07
    æ¯ķ
    0.07
    gue
    0.07
     about
    0.07
    igue
    0.07
     how
    0.07
    TINGS
    0.07
    Activations Density 0.009%

    No Known Activations