© 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. 16518
    Prev
    Next
    INDEX
    Explanations

    numbered lists or items related to quantitative data

    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
    ikut
    -0.06
    endra
    -0.06
    ipelines
    -0.06
    μαι
    -0.06
    reds
    -0.06
    arma
    -0.06
    reve
    -0.06
     sign
    -0.06
    adge
    -0.06
    Ń
    -0.06
    POSITIVE LOGITS
    éĥ¡
    0.07
    Ìģc
    0.07
    /english
    0.07
    vak
    0.07
    shiv
    0.06
    busy
    0.06
    HostException
    0.06
    Americ
    0.06
     Woo
    0.06
    imson
    0.06
    Activations Density 0.013%

    No Known Activations