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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17273
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "said" and similar reporting verbs

    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
    itti
    -0.06
    izza
    -0.06
    izard
    -0.06
    mer
    -0.06
    horn
    -0.06
    ulos
    -0.06
    rest
    -0.06
    ero
    -0.06
    227
    -0.06
     surrogate
    -0.06
    POSITIVE LOGITS
    è£ķ
    0.06
    (rawValue
    0.06
    istique
    0.06
    ģn
    0.06
     stru
    0.06
    OMET
    0.06
    yntax
    0.06
    ymbols
    0.06
     ä¸
    0.06
    VERR
    0.06
    Activations Density 0.003%

    No Known Activations