© 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. 125559
    Prev
    Next
    INDEX
    Explanations

    negative constructions beginning with "nor."

    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
    eer
    -0.08
    agle
    -0.07
    ylon
    -0.07
    392
    -0.07
    ees
    -0.07
    nt
    -0.07
    адÑĥ
    -0.07
    adÄĽ
    -0.07
    ted
    -0.07
    esty
    -0.07
    POSITIVE LOGITS
     does
    0.11
    wegian
    0.10
    theast
    0.09
    theless
    0.09
     did
    0.08
     tamp
    0.08
     any
    0.08
    thern
    0.07
     do
    0.07
    wich
    0.07
    Activations Density 0.007%

    No Known Activations