© 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. 16601
    Prev
    Next
    INDEX
    Explanations

    information regarding rewards offered for tips related to criminal activity

    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
     PIN
    -0.06
    gel
    -0.06
    hab
    -0.06
     Heller
    -0.06
     onCancel
    -0.06
    str
    -0.06
     continuity
    -0.06
    art
    -0.06
    ambi
    -0.06
    à¸Ńà¸Ń
    -0.06
    POSITIVE LOGITS
     Anonymous
    0.14
     anonymous
    0.14
     anonymity
    0.14
    Anonymous
    0.13
    anonymous
    0.13
     anonymously
    0.13
     anon
    0.11
     anonym
    0.10
    anon
    0.10
     confidential
    0.10
    Activations Density 0.037%

    No Known Activations