© 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. 75275
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate the end of sentences

    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
    endon
    -0.07
    dex
    -0.07
    ìĭ¬
    -0.07
    una
    -0.07
    enheim
    -0.06
    aiser
    -0.06
    ktop
    -0.06
    stal
    -0.06
    ).(
    -0.06
    .generated
    -0.06
    POSITIVE LOGITS
     then
    0.08
     upon
    0.07
     when
    0.07
    Rather
    0.07
     rather
    0.07
    bang
    0.07
     Vo
    0.07
     Gale
    0.06
     Rather
    0.06
     instead
    0.06
    Activations Density 0.051%

    No Known Activations