Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93890
    Prev
    Next
    INDEX
    Explanations

    occurrences of the function 'isset' commonly used in programming

    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
    role
    -0.08
    dda
    -0.08
    WithIdentifier
    -0.07
     Dawson
    -0.07
    PFN
    -0.07
    ared
    -0.07
    çı
    -0.07
    utas
    -0.07
    á»iji
    -0.07
    Gratis
    -0.07
    POSITIVE LOGITS
    ENCE
    0.07
    840
    0.06
    egov
    0.06
    opro
    0.06
    ments
    0.06
    ified
    0.06
    enville
    0.06
    ment
    0.06
    952
    0.06
     hyper
    0.06
    Activations Density 0.004%

    No Known Activations