© 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. 74765
    Prev
    Next
    INDEX
    Explanations

    financial metrics and regulatory language related to monetary penalties

    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
    isel
    -0.08
    vation
    -0.07
    -Semit
    -0.07
     eo
    -0.07
    égor
    -0.06
    á»Ĩ
    -0.06
    渡
    -0.06
     tá»Ń
    -0.06
    ãĥ¬ãĥĵ
    -0.06
    stanov
    -0.06
    POSITIVE LOGITS
     Bloomberg
    0.09
     Wal
    0.07
     Blanch
    0.06
     Photographer
    0.06
     capit
    0.06
    horn
    0.06
     disk
    0.06
     Vall
    0.06
    oppers
    0.06
    aktiv
    0.06
    Activations Density 0.010%

    No Known Activations