© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76660
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating emphasis or pauses in dialogue

    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
    oto
    -0.08
    #echo
    -0.07
    lier
    -0.07
    èo
    -0.07
    erre
    -0.07
     courier
    -0.07
    ẻ
    -0.07
    ór
    -0.07
    ampo
    -0.07
    Ñģим
    -0.06
    POSITIVE LOGITS
    ahlen
    0.06
    â̦↵↵↵
    0.06
     Hind
    0.06
     hind
    0.06
     vá»įng
    0.06
    rzy
    0.06
    -lnd
    0.06
     Ful
    0.06
     There
    0.06
    enty
    0.06
    Activations Density 0.013%

    No Known Activations