© 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. 93694
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation marks, particularly periods, indicating sentence endings

    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
     but
    -0.19
    but
    -0.16
     nhưng
    -0.15
     pero
    -0.15
     но
    -0.15
     however
    -0.14
     maar
    -0.14
    ï¼Įä½Ĩ
    -0.14
     However
    -0.14
     ÙĦÙĥÙĨ
    -0.14
    POSITIVE LOGITS
    æ¯ķ
    0.08
    åĨµ
    0.07
    _PUS
    0.07
    бо
    0.07
     indeed
    0.07
    ville
    0.07
    irut
    0.07
     ultimately
    0.07
    .GraphicsUnit
    0.07
     anyway
    0.06
    Activations Density 0.106%

    No Known Activations