© 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. 76642
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to characters or significant individuals

    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
    olu
    -0.07
    eline
    -0.06
    ixin
    -0.06
    ÐĬ
    -0.06
    Ìģ
    -0.06
    ontent
    -0.06
    Ir
    -0.06
    heits
    -0.06
    eç
    -0.06
    ãĤĪãģĨãģ«
    -0.06
    POSITIVE LOGITS
    adas
    0.08
    ---</
    0.07
     divers
    0.06
    wil
    0.06
     Afterwards
    0.06
    USA
    0.06
    wich
    0.06
     Äijỡ
    0.06
     CALLBACK
    0.06
    .serializer
    0.06
    Activations Density 0.000%

    No Known Activations