Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3628
    Prev
    Next
    INDEX
    Explanations

    technical issues related to software and systems errors

    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
     sore
    -0.08
    atra
    -0.06
    OUCH
    -0.06
    iddet
    -0.06
    mund
    -0.06
    awan
    -0.06
     slack
    -0.06
     Sad
    -0.06
    çĶļ
    -0.06
    Ùıس
    -0.06
    POSITIVE LOGITS
    ils
    0.08
     blah
    0.08
    ultz
    0.07
     encountered
    0.07
    elper
    0.07
    tons
    0.07
     exceeded
    0.07
    æī¾
    0.07
     Cannot
    0.06
    DCF
    0.06
    Activations Density 0.031%

    No Known Activations