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

    Neuronpedia

    Jacobian LensNEW
    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. 60725
    Prev
    Next
    INDEX
    Explanations

    instances of the word "position" in relation to numeric values

    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
    lore
    -0.08
    ogany
    -0.08
    mie
    -0.07
    essler
    -0.07
    apon
    -0.07
    é¾Ħ
    -0.07
    uya
    -0.07
    usal
    -0.07
    ends
    -0.07
    ansion
    -0.07
    POSITIVE LOGITS
    nement
    0.14
    ally
    0.13
    ality
    0.12
    naires
    0.11
    als
    0.10
    naire
    0.10
    nal
    0.09
    nist
    0.08
    amiento
    0.08
    ioned
    0.08
    Activations Density 0.062%

    No Known Activations