© 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. 86700
    Prev
    Next
    INDEX
    Explanations

    phrases related to discovery and establishment

    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
    оÑģÑĤÑĥп
    -0.08
    ahun
    -0.07
    akov
    -0.07
    Search
    -0.07
    orf
    -0.06
    ails
    -0.06
     search
    -0.06
    ÅĻád
    -0.06
    lical
    -0.06
    auc
    -0.06
    POSITIVE LOGITS
     itself
    0.07
    ry
    0.07
     expression
    0.06
    ered
    0.06
     space
    0.06
    رÙĬس
    0.06
     place
    0.06
    athers
    0.06
     discrim
    0.05
    spot
    0.05
    Activations Density 0.014%

    No Known Activations