© 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. 27956
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various methods or means of transmission

    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
    itemap
    -0.07
    inch
    -0.07
     respectively
    -0.06
     samt
    -0.06
    hlas
    -0.06
    etc
    -0.06
    acon
    -0.06
    prises
    -0.06
    pecially
    -0.06
    .framework
    -0.06
    POSITIVE LOGITS
     ranging
    0.10
     depending
    0.09
     including
    0.08
     varying
    0.08
     withd
    0.07
    ilos
    0.07
    depending
    0.07
     but
    0.07
    ults
    0.07
     different
    0.07
    Activations Density 0.034%

    No Known Activations