© 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 EvalsExportsAPI 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. 78560
    Prev
    Next
    INDEX
    Explanations

    references to sources or origins 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
    iveau
    -0.07
    EXTERN
    -0.07
    ÐĴС
    -0.07
    uids
    -0.07
    igsaw
    -0.07
    ONS
    -0.06
    ÑģÑĥÑĤ
    -0.06
    ureau
    -0.06
    egis
    -0.06
    bÃŃr
    -0.06
    POSITIVE LOGITS
    ëŁī
    0.06
     fauc
    0.06
    olumn
    0.06
    orf
    0.06
    stride
    0.06
     Siege
    0.06
    803
    0.06
    untu
    0.05
     Rodrig
    0.05
    OfDay
    0.05
    Activations Density 0.014%

    No Known Activations