© 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. 71154
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" in various contexts

    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
    ãģ¡ãĤĥãĤĵ
    -0.10
     célib
    -0.09
    gnore
    -0.09
    agnar
    -0.09
    IGHL
    -0.09
     ков
    -0.08
    TOTYPE
    -0.08
    abay
    -0.08
     ilet
    -0.08
    KeySpec
    -0.08
    POSITIVE LOGITS
     means
    0.13
     virtue
    0.12
    -products
    0.12
    products
    0.11
     the
    0.10
     a
    0.10
    /to
    0.09
    /from
    0.09
    -election
    0.09
    laws
    0.09
    Activations Density 0.341%

    No Known Activations