© 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. 55788
    Prev
    Next
    INDEX
    Explanations

    references to financial aspects related to projects or events

    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
    lag
    -0.07
    quo
    -0.07
    kel
    -0.06
    .§
    -0.06
    opp
    -0.06
    abe
    -0.06
    айд
    -0.06
     opp
    -0.06
    ".$_
    -0.06
    Tit
    -0.06
    POSITIVE LOGITS
     already
    0.14
    Already
    0.13
     Already
    0.13
    already
    0.13
    _already
    0.10
     Ñĥже
    0.10
    å·²ç»ı
    0.09
     bereits
    0.09
     irreversible
    0.09
     sudah
    0.09
    Activations Density 0.030%

    No Known Activations