© 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. 56196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assistance or suitability

    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
    ouch
    -0.08
    ibase
    -0.06
    POSIT
    -0.06
    pers
    -0.06
    ffen
    -0.06
    uki
    -0.06
    _FF
    -0.06
    OUCH
    -0.06
    cci
    -0.06
    mers
    -0.06
    POSITIVE LOGITS
    ÏĦÏį
    0.07
     bola
    0.07
    é£
    0.07
     buflen
    0.06
    paralle
    0.06
    nist
    0.06
    enko
    0.06
    noch
    0.06
    upe
    0.06
    itsu
    0.06
    Activations Density 0.003%

    No Known Activations