© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78912
    Prev
    Next
    INDEX
    Explanations

    references to authorship and publication-related terms

    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
    ick
    -0.07
    uman
    -0.07
     dus
    -0.06
     Nobel
    -0.06
    arrow
    -0.06
    iss
    -0.06
     hugs
    -0.06
     spokesperson
    -0.06
    शà¤ķ
    -0.06
    á»ķ
    -0.05
    POSITIVE LOGITS
    íıŃ
    0.09
     forthcoming
    0.08
     recently
    0.07
    .amazon
    0.07
     topo
    0.07
     blog
    0.07
    AGER
    0.06
    olit
    0.06
    elper
    0.06
    .Unmarshal
    0.06
    Activations Density 0.009%

    No Known Activations