© 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. 70403
    Prev
    Next
    INDEX
    Explanations

    phrases related to the theme of perseverance or effort in creative works

    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
    .yy
    -0.07
    евиÑĩ
    -0.07
     Leban
    -0.07
    èĢĥ
    -0.07
     shelves
    -0.07
    ÑģÑĤеÑĢ
    -0.07
    zion
    -0.07
    (ed
    -0.07
    ượt
    -0.07
    _ALIGNMENT
    -0.07
    POSITIVE LOGITS
    ulu
    0.08
     behalf
    0.08
     fronts
    0.08
     promises
    0.07
    isphere
    0.06
    otte
    0.06
     copp
    0.06
     promised
    0.06
    stadt
    0.06
    eworld
    0.06
    Activations Density 0.032%

    No Known Activations