© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107259
    Prev
    Next
    INDEX
    Explanations

    the phrase "into" in 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
    ase
    -0.07
    eda
    -0.07
    rit
    -0.07
    lant
    -0.06
    uÃŃ
    -0.06
     Heard
    -0.06
    itor
    -0.06
    amy
    -0.06
    aga
    -0.06
    FormattedMessage
    -0.06
    POSITIVE LOGITS
    аки
    0.07
    flen
    0.07
    akah
    0.07
     веÑĢеÑģ
    0.07
    еÑĢеÑĩ
    0.07
    coli
    0.06
    ocket
    0.06
     contact
    0.06
     lim
    0.06
     жовÑĤ
    0.06
    Activations Density 0.010%

    No Known Activations