© 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. 108494
    Prev
    Next
    INDEX
    Explanations

    possessive forms or constructions expressing ownership

    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
    uto
    -0.08
    sher
    -0.08
    ussen
    -0.07
    owo
    -0.06
    oad
    -0.06
    PARSE
    -0.06
    ìĭ¬
    -0.06
     konkrét
    -0.06
    lý
    -0.06
    casts
    -0.06
    POSITIVE LOGITS
     worth
    0.11
     Worth
    0.07
    éĴŁ
    0.07
    tÄĽ
    0.07
     Longitude
    0.07
    ãĤ·ãĥ¼
    0.07
    edn
    0.07
    moth
    0.07
    ches
    0.06
    ckill
    0.06
    Activations Density 0.007%

    No Known Activations