© 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. 126679
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to navigation functionality

    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
    ahoo
    -0.09
    oir
    -0.08
    _codegen
    -0.07
    ear
    -0.07
    adge
    -0.07
    ushman
    -0.07
    rana
    -0.07
     é«
    -0.07
    foy
    -0.07
    iena
    -0.06
    POSITIVE LOGITS
    umb
    0.06
    266
    0.06
    inal
    0.06
    unction
    0.06
    uster
    0.06
     Ø¢Ùħد
    0.06
    íĺģ
    0.06
     argc
    0.05
    ãĥĥ
    0.05
    agli
    0.05
    Activations Density 0.000%

    No Known Activations