© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    contrasting statements or ideas

    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
    odate
    -0.07
    oz
    -0.07
     initially
    -0.06
    .fm
    -0.06
    æĴ
    -0.06
    FromNib
    -0.06
    ngth
    -0.06
    ãĥ©ãĥ³ãĥī
    -0.06
    hos
    -0.06
    anco
    -0.06
    POSITIVE LOGITS
     when
    0.18
    when
    0.16
     When
    0.15
     quando
    0.14
     cuando
    0.14
    When
    0.14
    _when
    0.13
     khi
    0.12
     WHEN
    0.12
    	when
    0.12
    Activations Density 0.060%

    No Known Activations