© 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. 117889
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections, often using conjunctions and references to reality

    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
    áo
    -0.07
    psz
    -0.07
     erotische
    -0.07
    vero
    -0.06
     Oaks
    -0.06
    thon
    -0.06
     Äij
    -0.06
    ÑĤап
    -0.06
    наÑĤ
    -0.06
    kami
    -0.06
    POSITIVE LOGITS
    823
    0.07
     Mahm
    0.06
    γα
    0.06
    raud
    0.06
    vik
    0.06
    ãĥªãĥ³ãĤ°
    0.06
    vx
    0.06
    że
    0.06
    assage
    0.06
    λαν
    0.05
    Activations Density 0.024%

    No Known Activations