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

    Neuronpedia

    Jacobian LensNEW
    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. 87549
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions or affiliations

    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
    ÑĨеп
    -0.09
    .updateDynamic
    -0.09
    ãĥ§
    -0.08
    liž
    -0.08
    ɵ
    -0.08
     ört
    -0.07
    ForRow
    -0.07
    subjects
    -0.07
    endum
    -0.07
    /**č↵
    -0.07
    POSITIVE LOGITS
     former
    0.28
     Former
    0.24
    former
    0.23
    Former
    0.22
     býval
    0.16
     retired
    0.15
     erst
    0.14
     formerly
    0.13
     ex
    0.12
     سابÙĤ
    0.11
    Activations Density 0.095%

    No Known Activations