© 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. 126181
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant or key information

    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
    olec
    -0.06
    riter
    -0.06
    idal
    -0.06
    edList
    -0.05
     Dimit
    -0.05
    ADE
    -0.05
     incr
    -0.05
    apas
    -0.05
    дав
    -0.05
    ÑĩаÑģ
    -0.05
    POSITIVE LOGITS
    note
    0.09
     note
    0.09
     Note
    0.08
    aint
    0.07
    bish
    0.07
    bett
    0.07
    éļ
    0.07
    lum
    0.06
    Note
    0.06
    rier
    0.06
    Activations Density 0.010%

    No Known Activations