© 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. 94240
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions or conversational prompts

    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
     WTF
    -0.08
    .normalized
    -0.07
    .IsNullOr
    -0.07
    ÑĪев
    -0.07
    اÛĮد
    -0.07
    ÙĥÙĬÙĬÙģ
    -0.07
    اÙī
    -0.07
    ÙĪÙĤÙĬت
    -0.07
    eyn
    -0.07
    ftime
    -0.07
    POSITIVE LOGITS
     guess
    0.07
     ëĺIJ
    0.06
    ienne
    0.06
    ãģ¾ãģŁ
    0.06
    agle
    0.06
    adow
    0.06
    ops
    0.06
    ?
    0.06
     Ramp
    0.06
    ÑĢаÑģÑĤа
    0.05
    Activations Density 0.005%

    No Known Activations