© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60270
    Prev
    Next
    INDEX
    Explanations

    phrases indicating long-term implications or consequences

    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
    itm
    -0.08
     "---
    -0.06
    NSNotification
    -0.06
    ustin
    -0.06
     âĺħ
    -0.06
    ivated
    -0.06
    urus
    -0.06
    .guard
    -0.06
    issen
    -0.06
     etc
    -0.06
    POSITIVE LOGITS
    Nib
    0.09
    oe
    0.06
    ç£
    0.06
    tones
    0.06
    ROLS
    0.06
    agus
    0.06
    atro
    0.06
    Sac
    0.06
    oldem
    0.06
    QRS
    0.06
    Activations Density 0.006%

    No Known Activations