© 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. 28749
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence-ending patterns

    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
    illez
    -0.07
    iesel
    -0.07
    nip
    -0.07
    OOT
    -0.07
    egot
    -0.07
    lease
    -0.07
    aily
    -0.07
    ouz
    -0.07
    Ñıг
    -0.07
    éis
    -0.07
    POSITIVE LOGITS
     why
    0.10
    why
    0.08
     how
    0.07
    pher
    0.07
     plus
    0.06
     pourquoi
    0.06
     WHY
    0.06
     cómo
    0.06
    ber
    0.06
    )did
    0.06
    Activations Density 0.008%

    No Known Activations