© 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. 120540
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and formatting cues in text

    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
    ÑĪов
    -0.07
    SSF
    -0.07
    ìľµ
    -0.06
    ứng
    -0.06
    //{{
    -0.06
    á»įng
    -0.06
    CEF
    -0.06
    andom
    -0.06
    atre
    -0.06
    illac
    -0.06
    POSITIVE LOGITS
    tractor
    0.07
     Depending
    0.07
    Depending
    0.07
     depending
    0.07
     Alternatively
    0.06
    ÅĽci
    0.06
    either
    0.06
    ipi
    0.06
     blat
    0.06
    apa
    0.06
    Activations Density 0.010%

    No Known Activations