© 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. 60759
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions indicating transitions in a narrative or argument

    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
    овиÑĩ
    -0.08
    uch
    -0.07
    åħ¶
    -0.07
    Äįer
    -0.07
    .scalablytyped
    -0.07
    -Assad
    -0.07
    opping
    -0.07
    ÑĮ
    -0.07
    abr
    -0.06
     parach
    -0.06
    POSITIVE LOGITS
    ouri
    0.07
    'gc
    0.06
    anut
    0.06
    elp
    0.06
     full
    0.06
    atty
    0.06
    /no
    0.06
    .liferay
    0.06
    0.06
    tered
    0.06
    Activations Density 0.031%

    No Known Activations