© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    expressions related to abuse and its consequences

    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
     even
    -0.10
    even
    -0.09
    çĶļèĩ³
    -0.07
     nawet
    -0.07
     whole
    -0.07
     Even
    -0.07
     despite
    -0.07
     both
    -0.06
     даже
    -0.06
     directly
    -0.06
    POSITIVE LOGITS
     thôi
    0.12
    ãģŁãģł
    0.09
    .scalablytyped
    0.08
    ç½
    0.08
     saja
    0.08
    Certain
    0.08
    ä¸Ģç§į
    0.08
     occasionally
    0.08
     Occasionally
    0.08
     Certain
    0.08
    Activations Density 0.061%

    No Known Activations