© 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. 17-LLAMASCOPE-RES-131K
    11. 55732
    Prev
    Next
    INDEX
    Explanations

    instances of the substring "st"

    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
    ogi
    -0.07
    afort
    -0.07
    uela
    -0.07
    izard
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    ãĥ¼ãĥ¬
    -0.06
    fh
    -0.06
    izzo
    -0.06
    mom
    -0.06
    ạt
    -0.06
    POSITIVE LOGITS
     SND
    0.07
     Hed
    0.06
    agar
    0.06
    .scalablytyped
    0.06
    ye
    0.06
     creampie
    0.06
    tees
    0.06
     Silk
    0.06
    cko
    0.06
    ige
    0.06
    Activations Density 0.000%

    No Known Activations