© 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. 9-LLAMASCOPE-RES-131K
    11. 98224
    Prev
    Next
    INDEX
    Explanations

    time-related information and specific timestamps

    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
     invariant
    -0.07
    andas
    -0.07
    i
    -0.06
    n
    -0.06
    -0.06
    it
    -0.06
     -
    -0.06
    846
    -0.06
     '
    -0.05
    abra
    -0.05
    POSITIVE LOGITS
    pheric
    0.08
    EncodingException
    0.08
    \Migrations
    0.08
     pÅĻiv
    0.07
    ŀĭ
    0.07
    AndServe
    0.07
    )size
    0.07
    å¼¥
    0.07
    GRP
    0.07
     '",
    0.07
    Activations Density 0.017%

    No Known Activations