© 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. 108320
    Prev
    Next
    INDEX
    Explanations

    verbs and their variations representing actions or tasks

    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
    оза
    -0.07
     actionTypes
    -0.07
    çĩ
    -0.07
    ra
    -0.06
    burg
    -0.06
    á»ī
    -0.06
    phins
    -0.06
    ynth
    -0.06
    ologne
    -0.06
    stuff
    -0.06
    POSITIVE LOGITS
     google
    0.07
    ÑĴ
    0.06
    jezd
    0.06
     carbon
    0.06
     test
    0.06
    âĶĶ
    0.06
    }elseif
    0.06
    icated
    0.06
    ÂĢÂĻ
    0.06
     Google
    0.06
    Activations Density 0.022%

    No Known Activations