© 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 EvalsExportsAPI 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. 29323
    Prev
    Next
    INDEX
    Explanations

    relationships involving changes in frequency and amplitude in a wave context

    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
    linger
    -0.07
    eki
    -0.07
     dot
    -0.06
    ekli
    -0.06
    umd
    -0.06
    tright
    -0.06
    acl
    -0.06
     COPYRIGHT
    -0.06
    shine
    -0.06
    lectron
    -0.06
    POSITIVE LOGITS
     cÃłng
    0.11
     increasing
    0.10
     increasingly
    0.09
    è¶Ĭ
    0.09
     increase
    0.09
    incre
    0.08
     Increasing
    0.08
     increases
    0.08
     Increase
    0.08
    increase
    0.07
    Activations Density 0.060%

    No Known Activations