© 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. 129881
    Prev
    Next
    INDEX
    Explanations

    themes of personal growth and empowerment through experiences and relationships

    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
    oles
    -0.07
    StateManager
    -0.06
    indy
    -0.06
    uffer
    -0.06
     táºŃn
    -0.06
    burg
    -0.06
    دÙĩÙħ
    -0.06
     tongues
    -0.06
    ond
    -0.06
    CC
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    anzi
    0.07
    ezi
    0.07
    imulation
    0.07
    ailable
    0.07
    ÑĢаÑĤно
    0.06
     tane
    0.06
    contri
    0.06
     Advoc
    0.06
    reate
    0.06
    Activations Density 0.028%

    No Known Activations