© 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. 74911
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "as" 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
    antor
    -0.07
    ãĥĥãĥģ
    -0.07
    ohan
    -0.07
    озна
    -0.07
     Cant
    -0.07
    ombine
    -0.07
    istrovstvÃŃ
    -0.07
     olm
    -0.07
    offee
    -0.07
    udson
    -0.07
    POSITIVE LOGITS
     result
    0.13
     consequence
    0.10
    result
    0.08
     directly
    0.08
    Result
    0.07
     part
    0.07
     Result
    0.07
     resultado
    0.07
     aftermath
    0.07
    (result
    0.07
    Activations Density 0.009%

    No Known Activations