© 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. 17-LLAMASCOPE-RES-131K
    11. 41489
    Prev
    Next
    INDEX
    Explanations

    references to names and significant figures in historical or formal contexts

    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
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    ummer
    -0.07
    izu
    -0.06
     emploi
    -0.06
    вид
    -0.06
    PCS
    -0.06
    icens
    -0.06
    ']=="
    -0.06
    UBY
    -0.06
    неÑģ
    -0.06
    POSITIVE LOGITS
    /name
    0.08
     named
    0.08
    952
    0.07
     name
    0.07
    named
    0.07
    utz
    0.07
    /by
    0.06
    åIJįåŃĹ
    0.06
    ansa
    0.06
    SimpleName
    0.06
    Activations Density 0.005%

    No Known Activations