© 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. 61666
    Prev
    Next
    INDEX
    Explanations

    programming concepts and constructs related to Java object classes and methods

    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
    -mf
    -0.09
    itesse
    -0.09
    fsp
    -0.08
    rego
    -0.08
    drv
    -0.08
     baiser
    -0.08
    onaut
    -0.08
    à¸į
    -0.08
    sing
    -0.07
    ieber
    -0.07
    POSITIVE LOGITS
    410
    0.07
    uem
    0.07
    émon
    0.06
    icz
    0.06
    WG
    0.06
    ensa
    0.06
    upe
    0.05
    wg
    0.05
    ény
    0.05
     GAP
    0.05
    Activations Density 0.003%

    No Known Activations