© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 62481
    Prev
    Next
    INDEX
    Explanations

    characters or letters with particular frequency patterns

    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
    illis
    -0.09
    ť
    -0.08
    unga
    -0.08
     tarif
    -0.08
     =================================================================================
    -0.07
     HEAP
    -0.07
    ãĥĨãĥ«
    -0.07
    imson
    -0.07
    eniz
    -0.07
    ëł¹
    -0.07
    POSITIVE LOGITS
    OLEAN
    0.07
    esel
    0.06
     @{$
    0.06
    gos
    0.06
    ools
    0.06
    agen
    0.06
    osl
    0.06
     Kob
    0.06
     padd
    0.05
     song
    0.05
    Activations Density 0.080%

    No Known Activations