© 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. 57710
    Prev
    Next
    INDEX
    Explanations

    references to fame or famous individuals

    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
    tsy
    -0.08
    shal
    -0.08
    ument
    -0.08
    sWith
    -0.07
    izen
    -0.07
    izabeth
    -0.07
    izens
    -0.07
    ootball
    -0.07
    tings
    -0.07
    że
    -0.07
    POSITIVE LOGITS
    ess
    0.10
    ness
    0.08
     enough
    0.08
    esson
    0.07
    eness
    0.07
    nis
    0.07
    oft
    0.06
    land
    0.06
     Stern
    0.06
     Kear
    0.06
    Activations Density 0.006%

    No Known Activations