Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95927
    Prev
    Next
    INDEX
    Explanations

    affirmations of evidence or truth

    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
    ksen
    -0.07
    uchi
    -0.07
    mage
    -0.07
    gaard
    -0.06
    omens
    -0.06
    utin
    -0.06
    _HS
    -0.06
    asurement
    -0.06
    μÏĨ
    -0.06
    ovic
    -0.06
    POSITIVE LOGITS
    dol
    0.08
    aines
    0.07
    olv
    0.06
     رأ
    0.06
    art
    0.06
    iyas
    0.06
     Sho
    0.06
    dül
    0.06
    aul
    0.06
     mimeType
    0.06
    Activations Density 0.018%

    No Known Activations