© 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. 14805
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical attributes or conditions of items

    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
    cház
    -0.08
    opies
    -0.08
    ProgressHUD
    -0.07
    ाहà¤ķ
    -0.07
    anic
    -0.07
    eldon
    -0.07
    нÑıÑĤÑĤÑı
    -0.07
    ftime
    -0.07
    충
    -0.07
    opoulos
    -0.07
    POSITIVE LOGITS
    kin
    0.07
    pong
    0.07
    ye
    0.07
     along
    0.06
    oth
    0.06
    alf
    0.06
    ноÑģÑĤей
    0.06
     Lindsey
    0.06
    urs
    0.06
    orm
    0.06
    Activations Density 0.000%

    No Known Activations