© 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. 106864
    Prev
    Next
    INDEX
    Explanations

    references to scalar quantities and their properties in scientific contexts

    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
    asic
    -0.07
    enci
    -0.07
    rale
    -0.07
    rosso
    -0.07
    iam
    -0.07
    ees
    -0.06
     swe
    -0.06
    <[
    -0.06
    uttgart
    -0.06
    nt
    -0.06
    POSITIVE LOGITS
    (es
    0.07
    readcr
    0.06
    одав
    0.06
    Animator
    0.06
    cury
    0.06
     Tide
    0.06
    CompanyId
    0.06
    ınca
    0.06
    omes
    0.06
    Anywhere
    0.06
    Activations Density 0.006%

    No Known Activations