© 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. 9-LLAMASCOPE-RES-131K
    11. 95633
    Prev
    Next
    INDEX
    Explanations

    references to cultural or historical symbols

    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
    uzey
    -0.08
    zung
    -0.07
    acf
    -0.07
    zb
    -0.07
    DataTask
    -0.07
    imeo
    -0.07
    vig
    -0.07
    .GraphicsUnit
    -0.07
    onda
    -0.07
    inea
    -0.07
    POSITIVE LOGITS
     Pur
    0.06
     Chest
    0.06
     accord
    0.06
    esch
    0.06
    èħ¿
    0.06
    cho
    0.06
     WWW
    0.06
     Cho
    0.06
    242
    0.05
    holm
    0.05
    Activations Density 0.008%

    No Known Activations