© 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. 5-LLAMASCOPE-RES-131K
    11. 125932
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicles and traffic incidents

    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
    orthand
    -0.08
    ãĥ©ãĥ¼
    -0.08
    eling
    -0.07
    edn
    -0.07
    loo
    -0.07
    й
    -0.07
    Computed
    -0.07
    entimes
    -0.07
    -tm
    -0.06
     tvb
    -0.06
    POSITIVE LOGITS
    UME
    0.06
    İ
    0.06
    igt
    0.06
     elsewhere
    0.06
    _NS
    0.06
    _FM
    0.05
    lane
    0.05
    .standard
    0.05
    sons
    0.05
    vsp
    0.05
    Activations Density 0.001%

    No Known Activations