© 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. 128414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of specific conditions, entities, or quantities

    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
    venience
    -0.07
     zas
    -0.07
    ilon
    -0.06
    å°ĭ
    -0.06
    NECT
    -0.06
    ноÑģÑıÑĤ
    -0.06
    misc
    -0.06
    -expanded
    -0.06
    ANDLE
    -0.06
    dismiss
    -0.06
    POSITIVE LOGITS
    $MESS
    0.09
     traces
    0.07
    fad
    0.07
    éĩı
    0.06
    robe
    0.06
     element
    0.06
    cona
    0.06
     elements
    0.06
    ilities
    0.06
    place
    0.06
    Activations Density 0.030%

    No Known Activations