© 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. 75023
    Prev
    Next
    INDEX
    Explanations

    occurrences of the sequence "nd" across various contexts

    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
    imson
    -0.08
    lesen
    -0.08
    awk
    -0.07
    mlin
    -0.07
    isz
    -0.07
    erot
    -0.07
    encil
    -0.07
    legt
    -0.07
    bral
    -0.07
    dest
    -0.07
    POSITIVE LOGITS
    ividual
    0.08
    ity
    0.07
    ever
    0.07
    epend
    0.06
    aker
    0.06
     prec
    0.06
    aine
    0.06
     precursor
    0.06
    Unnamed
    0.06
    orm
    0.06
    Activations Density 0.009%

    No Known Activations