© 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. 126436
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases and arrests

    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
    swire
    -0.10
    ICODE
    -0.08
    adors
    -0.08
    cbc
    -0.08
    amo
    -0.08
    grily
    -0.07
    marshaller
    -0.07
    аниÑĨ
    -0.07
    /testify
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
    uja
    0.06
    ensation
    0.06
     true
    0.06
     sign
    0.06
    0.05
     log
    0.05
     hor
    0.05
     multiple
    0.05
     Athena
    0.05
    ius
    0.05
    Activations Density 0.012%

    No Known Activations