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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41501
    Prev
    Next
    INDEX
    Explanations

    phrases and punctuation that indicate parenthetical statements or asides within the text

    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
    oui
    -0.08
    елÑİ
    -0.07
     nid
    -0.07
    okens
    -0.07
    atrix
    -0.07
    asa
    -0.07
     symp
    -0.07
    Ïİ
    -0.07
    atorium
    -0.07
    dad
    -0.07
    POSITIVE LOGITS
    ãĥ³ãĥĸ
    0.06
    nier
    0.06
    rz
    0.06
    cen
    0.06
    154
    0.06
     uncon
    0.06
     feminine
    0.06
     settlements
    0.06
     settlement
    0.06
     masculine
    0.06
    Activations Density 0.021%

    No Known Activations