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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28833
    Prev
    Next
    INDEX
    Explanations

    instances of descriptive phrases and their attributes

    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
     itself
    -0.10
    deo
    -0.07
    aign
    -0.07
    inder
    -0.06
    moon
    -0.06
     Mim
    -0.06
     Waters
    -0.06
     Its
    -0.06
    quia
    -0.06
    lech
    -0.06
    POSITIVE LOGITS
     themselves
    0.09
     Ñģами
    0.07
    ionales
    0.07
     yourselves
    0.07
    ove
    0.06
    /problems
    0.06
    agrams
    0.06
     subset
    0.06
    ãĥ³ãĥĦ
    0.06
    iversit
    0.06
    Activations Density 0.063%

    No Known Activations