© 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. 75253
    Prev
    Next
    INDEX
    Explanations

    urls and symbols indicating links 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
    statistics
    -0.07
    als
    -0.06
    á»ĭnh
    -0.06
    abel
    -0.06
     Kub
    -0.06
    alg
    -0.06
    ocol
    -0.06
    iolet
    -0.06
    erable
    -0.06
    rescia
    -0.06
    POSITIVE LOGITS
    港
    0.06
    emade
    0.06
    CORD
    0.06
    ELLOW
    0.06
    ìĤ¼
    0.06
     ucwords
    0.06
    .simps
    0.06
    çı
    0.06
    ondo
    0.06
    tweet
    0.06
    Activations Density 0.030%

    No Known Activations