© 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. 74693
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'h'

    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
    uggle
    -0.06
    ourd
    -0.06
    fty
    -0.06
    pos
    -0.06
     pos
    -0.06
     Glad
    -0.05
    hti
    -0.05
     est
    -0.05
    Äįku
    -0.05
    oten
    -0.05
    POSITIVE LOGITS
    alloca
    0.08
    zia
    0.08
    ç§ģãģ®
    0.07
    stdcall
    0.07
    edImage
    0.07
    ieee
    0.07
    λÏī
    0.07
    .scalablytyped
    0.07
    å¸ĸ
    0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.07
    Activations Density 0.000%

    No Known Activations