© 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. 39563
    Prev
    Next
    INDEX
    Explanations

    names and terms related to individuals or entities, particularly those with 'Abhinav' or 'Abubakar'

    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
    plib
    -0.06
     Chips
    -0.06
    pek
    -0.06
    ohan
    -0.06
    frey
    -0.06
    verty
    -0.06
    877
    -0.06
    juan
    -0.06
    ÙĬÙĬر
    -0.06
    swagger
    -0.06
    POSITIVE LOGITS
    querque
    0.09
    antly
    0.08
    aben
    0.07
     ab
    0.07
    OVE
    0.07
     Ab
    0.07
    icht
    0.07
    afia
    0.07
    stand
    0.07
    ridged
    0.07
    Activations Density 0.019%

    No Known Activations