© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85261
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that indicate significant belief systems and ideological expressions

    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
    iveau
    -0.10
    illez
    -0.08
    otts
    -0.07
    ozo
    -0.07
    osit
    -0.07
    Å¡tÄĽ
    -0.07
    osi
    -0.07
    JECTION
    -0.07
     alongside
    -0.07
    ionage
    -0.07
    POSITIVE LOGITS
     resulting
    0.10
     alike
    0.08
     respectively
    0.08
     thus
    0.08
     Together
    0.07
     between
    0.07
     resultant
    0.07
     mutual
    0.07
     together
    0.07
     BOTH
    0.07
    Activations Density 0.069%

    No Known Activations