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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4281
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'Z'

    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
    rum
    -0.06
    ivre
    -0.06
    jem
    -0.06
    ithe
    -0.06
    .answers
    -0.06
    430
    -0.06
    672
    -0.06
    882
    -0.06
    istence
    -0.06
    ag
    -0.05
    POSITIVE LOGITS
    107
    0.07
     æģ
    0.06
    SKU
    0.06
    undler
    0.06
    amenti
    0.06
     srand
    0.06
    ilent
    0.06
     Fitz
    0.06
    inheritDoc
    0.06
    asn
    0.06
    Activations Density 0.007%

    No Known Activations