© 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. 15-LLAMASCOPE-RES-131K
    11. 62166
    Prev
    Next
    INDEX
    Explanations

    programming object types related to strings

    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
    otch
    -0.07
    ombat
    -0.07
     Vas
    -0.06
    ovat
    -0.06
    ascal
    -0.06
    aste
    -0.06
     skew
    -0.06
    æĬľ
    -0.06
    amedi
    -0.06
    athering
    -0.06
    POSITIVE LOGITS
    975
    0.07
    ãģıãĤĮ
    0.06
    adık
    0.06
    ,json
    0.06
    ãĤŃãĥ³ãĤ°
    0.06
    BackingField
    0.06
     ÑĪи
    0.06
    ÑĥÑĢа
    0.06
     tatto
    0.06
    PÅĻi
    0.06
    Activations Density 0.000%

    No Known Activations