© 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. 22-LLAMASCOPE-RES-131K
    11. 4270
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting used in citations or references

    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
    à¹Ģà¸Ī
    -0.07
    ÅĪ
    -0.06
     constitution
    -0.06
    roken
    -0.06
     ball
    -0.06
    ijkstra
    -0.06
     misc
    -0.06
    ayo
    -0.06
    spacer
    -0.06
     exponent
    -0.05
    POSITIVE LOGITS
    .MEDIA
    0.10
     media
    0.08
    ILER
    0.08
     Media
    0.08
     MEDIA
    0.08
     about
    0.08
     press
    0.08
    /media
    0.07
    Follow
    0.07
    -media
    0.07
    Activations Density 0.005%

    No Known Activations