© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74805
    Prev
    Next
    INDEX
    Explanations

    frequency of specific structural elements in the text, such as punctuation and town-related identifiers

    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
    IMO
    -0.06
    Fluid
    -0.06
     Fluid
    -0.06
     Bac
    -0.06
    -fluid
    -0.06
     addObject
    -0.06
     Pap
    -0.06
    rite
    -0.06
    aper
    -0.06
    çľģ
    -0.05
    POSITIVE LOGITS
     population
    0.08
    erah
    0.07
    à¹īà¸Ńà¸Ļ
    0.06
     Hook
    0.06
    illet
    0.06
    ErrorException
    0.06
    pany
    0.06
     pobl
    0.06
    -hook
    0.06
    AtA
    0.06
    Activations Density 0.004%

    No Known Activations