© 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. 75758
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate composition or structure

    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
    ish
    -0.07
    jong
    -0.07
    anson
    -0.06
    assing
    -0.06
    ghi
    -0.06
    yst
    -0.06
    Tile
    -0.06
    raud
    -0.06
    eri
    -0.06
     Cros
    -0.06
    POSITIVE LOGITS
    antly
    0.10
     of
    0.08
     adm
    0.07
     Ñģобой
    0.07
    probe
    0.07
    uate
    0.07
    ãĥ¶
    0.07
    ään
    0.06
    Probe
    0.06
    ointments
    0.06
    Activations Density 0.009%

    No Known Activations