© 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. 27761
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the name "Ch" and associated phrases related to it

    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
    gether
    -0.07
    iversal
    -0.07
    locked
    -0.07
    actly
    -0.06
    ayette
    -0.06
    egrated
    -0.06
    porter
    -0.06
     gest
    -0.06
    folio
    -0.06
    ouch
    -0.05
    POSITIVE LOGITS
    bie
    0.09
    s
    0.08
    orem
    0.08
    Ī¬
    0.07
    sWith
    0.07
    esco
    0.07
    izar
    0.07
    ORIZONTAL
    0.07
    sy
    0.07
    sim
    0.07
    Activations Density 0.007%

    No Known Activations