© 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. 58790
    Prev
    Next
    INDEX
    Explanations

    instances of frequency-related phrases and activities

    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
     everywhere
    -0.08
     поÑģÑĤоÑıнно
    -0.07
     constantly
    -0.07
    Ùİج
    -0.07
    amina
    -0.07
    prung
    -0.07
     constant
    -0.06
    764
    -0.06
     Lots
    -0.06
    vek
    -0.06
    POSITIVE LOGITS
     occasionally
    0.17
     occasional
    0.15
     Occasionally
    0.14
     sometimes
    0.13
     occas
    0.12
     ocas
    0.12
    occ
    0.11
    Occ
    0.11
     occ
    0.10
    sometimes
    0.10
    Activations Density 0.048%

    No Known Activations