© 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. 27451
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to specific subjects

    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
    ngr
    -0.08
    ing
    -0.08
    istrovstvÃŃ
    -0.08
     же
    -0.08
    oker
    -0.07
    /from
    -0.07
    -fashioned
    -0.07
    aliz
    -0.07
    alama
    -0.07
    otes
    -0.07
    POSITIVE LOGITS
    -HT
    0.11
    teenth
    0.09
    де
    0.09
    ëģĶ
    0.09
    ers
    0.09
    th
    0.08
    -star
    0.08
    0.08
    ermen
    0.08
    erman
    0.07
    Activations Density 0.381%

    No Known Activations