© 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. 76769
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters 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
    activex
    -0.08
     Kapoor
    -0.07
    ervice
    -0.07
    ãģ£ãģ±
    -0.07
    evin
    -0.07
    å½
    -0.06
    odos
    -0.06
    Ú¾
    -0.06
     ``(
    -0.06
    hp
    -0.06
    POSITIVE LOGITS
    anche
    0.09
    ombo
    0.06
    usc
    0.06
    ukes
    0.06
    antes
    0.06
    tea
    0.06
    uan
    0.06
    995
    0.06
    202
    0.06
    .sponge
    0.06
    Activations Density 0.046%

    No Known Activations