© 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. 17-LLAMASCOPE-RES-131K
    11. 55872
    Prev
    Next
    INDEX
    Explanations

    terms related to optionality and the handling of optional values 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
    à¥įवव
    -0.06
     jspb
    -0.06
    sal
    -0.06
    ColumnsMode
    -0.06
    ADED
    -0.06
     sessuali
    -0.06
    격
    -0.06
    OMET
    -0.06
    endas
    -0.06
    ë°į
    -0.06
    POSITIVE LOGITS
    /not
    0.08
    NESS
    0.07
    305
    0.07
    embro
    0.07
    _else
    0.07
    /null
    0.07
    ownik
    0.06
    çī
    0.06
    eft
    0.06
    estroy
    0.06
    Activations Density 0.002%

    No Known Activations