© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 57798
    Prev
    Next
    INDEX
    Explanations

    phrases pertaining to governance or organizational practices

    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
     kys
    -0.06
     poil
    -0.06
     intervening
    -0.06
     Patel
    -0.06
     pob
    -0.06
    ãĥĪãĥ«
    -0.06
    plex
    -0.06
    ahu
    -0.06
    ival
    -0.06
    mans
    -0.06
    POSITIVE LOGITS
     accompanied
    0.11
     acompañ
    0.10
     acompanh
    0.09
     accompanies
    0.08
     accompagn
    0.08
    ä¼´
    0.08
     translate
    0.08
    Translate
    0.08
     ÑģопÑĢов
    0.08
    accom
    0.07
    Activations Density 0.050%

    No Known Activations