© 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. 86095
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specificity or provide emphasis on details

    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
    regor
    -0.07
    sto
    -0.07
    gba
    -0.07
    hle
    -0.07
    ahun
    -0.07
    uder
    -0.07
    emble
    -0.07
    edn
    -0.07
    ultiply
    -0.07
    ein
    -0.07
    POSITIVE LOGITS
    ybrid
    0.07
    som
    0.06
     complement
    0.06
     HOLDERS
    0.06
    ibs
    0.06
    INGLE
    0.06
    çŃĭ
    0.06
    oldt
    0.06
    _KEYWORD
    0.06
    suite
    0.05
    Activations Density 0.085%

    No Known Activations