© 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. 106250
    Prev
    Next
    INDEX
    Explanations

    references to various forms of visual media, such as photographs and pictures

    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
    266
    -0.07
    wn
    -0.06
    isseur
    -0.06
    å®ĺ
    -0.05
    kie
    -0.05
    ems
    -0.05
    OH
    -0.05
    oci
    -0.05
    lee
    -0.05
    ng
    -0.05
    POSITIVE LOGITS
    !=(
    0.07
    vertiser
    0.07
    Äįky
    0.07
    terior
    0.07
    vidence
    0.07
    icky
    0.07
    lbrace
    0.07
    //[
    0.07
    .Broadcast
    0.07
    antan
    0.06
    Activations Density 0.013%

    No Known Activations