© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94591
    Prev
    Next
    INDEX
    Explanations

    the word "For" used in various contexts throughout the text

    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
    egrated
    -0.08
    ural
    -0.07
    $MESS
    -0.07
    aturated
    -0.06
    áš
    -0.06
    FO
    -0.06
    eli
    -0.06
    enga
    -0.06
    iad
    -0.06
    isclosed
    -0.06
    POSITIVE LOGITS
    VERR
    0.08
    ÑĢак
    0.07
    utin
    0.07
     nữa
    0.07
    .dim
    0.06
    ulk
    0.06
    inesis
    0.06
    ÑĢиг
    0.06
    anan
    0.06
    енз
    0.06
    Activations Density 0.008%

    No Known Activations