© 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. 105848
    Prev
    Next
    INDEX
    Explanations

    expressions indicating transitional phases or moments of change

    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
    -0.07
    385
    -0.06
     vs
    -0.06
    rella
    -0.06
     bid
    -0.06
    apia
    -0.06
     relevance
    -0.05
    uer
    -0.05
    anch
    -0.05
    VL
    -0.05
    POSITIVE LOGITS
    uckle
    0.08
     Stage
    0.07
     hete
    0.07
     unfavor
    0.07
     era
    0.07
    Pocket
    0.07
     stage
    0.07
    now
    0.07
    omorphic
    0.07
    ãĥ³ãĥĸ
    0.07
    Activations Density 0.025%

    No Known Activations