© 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. 126056
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or structures 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
    ands
    -0.07
    lea
    -0.07
    ä¿Ĭ
    -0.07
    åħį
    -0.06
    rine
    -0.06
    elas
    -0.06
    .BL
    -0.06
    vidence
    -0.06
    имÑĥ
    -0.06
    .sap
    -0.06
    POSITIVE LOGITS
    entiful
    0.08
    inus
    0.07
    UIStoryboardSegue
    0.07
    -valu
    0.07
    MBProgressHUD
    0.06
     NSCoder
    0.06
    ocker
    0.06
    'gc
    0.06
    olleyError
    0.06
    aci
    0.06
    Activations Density 0.012%

    No Known Activations