© 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. 76104
    Prev
    Next
    INDEX
    Explanations

    references to the extent or magnitude of various conditions or phenomena

    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
    afen
    -0.07
    shal
    -0.07
     corrid
    -0.06
    ysqli
    -0.06
    yang
    -0.06
    á»ģn
    -0.06
    jem
    -0.06
    ibu
    -0.06
    isper
    -0.06
    pers
    -0.06
    POSITIVE LOGITS
     damage
    0.08
     effort
    0.07
    _damage
    0.07
    damage
    0.07
    ãĥ¼ãĥĢ
    0.07
    ailer
    0.07
    RuntimeObject
    0.07
     depart
    0.07
    amage
    0.07
    illac
    0.07
    Activations Density 0.026%

    No Known Activations