© 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. 60755
    Prev
    Next
    INDEX
    Explanations

    references to probability or likelihood

    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
    ACHINE
    -0.07
     /^(
    -0.07
    etc
    -0.07
     kıs
    -0.06
    unate
    -0.06
    asser
    -0.06
    osi
    -0.06
    ãģĭãģ«
    -0.06
    BJECT
    -0.06
    verted
    -0.06
    POSITIVE LOGITS
    eck
    0.07
    ÏĦικ
    0.07
    kenin
    0.06
     none
    0.06
     likely
    0.06
     there
    0.06
     bahwa
    0.06
     rằng
    0.06
    SYM
    0.06
    -none
    0.06
    Activations Density 0.002%

    No Known Activations