© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57583
    Prev
    Next
    INDEX
    Explanations

    words that indicate a sense of complexity or detail

    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
    stroy
    -0.08
    edException
    -0.07
    atel
    -0.07
    ovÃŃ
    -0.06
    eriod
    -0.06
    égor
    -0.06
    eru
    -0.06
    eee
    -0.06
    ÏīÏĤ
    -0.06
    legg
    -0.06
    POSITIVE LOGITS
    -and
    0.12
     &
    0.11
    _and
    0.09
     and
    0.09
    &
    0.08
     AND
    0.08
     и
    0.07
     And
    0.07
    -&
    0.07
     &↵
    0.06
    Activations Density 0.022%

    No Known Activations