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. 75007
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to context, timeout, and item handling

    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
    368
    -0.07
    ardon
    -0.07
    åıĬåħ¶
    -0.07
    ÑĢоÑĩ
    -0.07
    åŀĭ
    -0.07
    idl
    -0.07
    ĨĴ
    -0.07
    à¤Ī
    -0.06
    oth
    -0.06
    ETO
    -0.06
    POSITIVE LOGITS
    vio
    0.06
    =true
    0.06
    iani
    0.06
    ABEL
    0.06
    :true
    0.06
    strup
    0.06
    tej
    0.06
    =True
    0.06
     ?><?
    0.06
     mish
    0.06
    Activations Density 0.027%

    No Known Activations