© 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. 15-LLAMASCOPE-RES-131K
    11. 886
    Prev
    Next
    INDEX
    Explanations

    phrases indicating social dynamics and status

    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
    atern
    -0.06
    brid
    -0.06
    olem
    -0.06
    à¸Ħำ
    -0.06
     Braves
    -0.06
    bes
    -0.06
     fond
    -0.06
     mart
    -0.06
    sd
    -0.06
    ances
    -0.06
    POSITIVE LOGITS
    assin
    0.08
    alic
    0.07
    ubic
    0.07
    NAMESPACE
    0.07
    éal
    0.07
    hatt
    0.06
    imu
    0.06
    azor
    0.06
    _TP
    0.06
    nila
    0.06
    Activations Density 0.067%

    No Known Activations