© 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. 15-LLAMASCOPE-RES-131K
    11. 103996
    Prev
    Next
    INDEX
    Explanations

    discussions of philosophical critique and theory

    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
     ranch
    -0.07
    occo
    -0.06
     season
    -0.06
     administration
    -0.06
    ale
    -0.06
     trif
    -0.06
    obo
    -0.06
    kw
    -0.06
     sole
    -0.06
     Benef
    -0.06
    POSITIVE LOGITS
    ubre
    0.07
    licer
    0.07
    licos
    0.07
     Yates
    0.07
    UInteger
    0.07
    IDGET
    0.07
    μή
    0.07
    eway
    0.07
    .raises
    0.07
    ÃŃses
    0.07
    Activations Density 0.086%

    No Known Activations