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. 84326
    Prev
    Next
    INDEX
    Explanations

    activities and programs for children and adolescents

    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
     serge
    -0.06
    жд
    -0.06
    argas
    -0.06
    argo
    -0.06
    rouch
    -0.06
    allo
    -0.06
    essler
    -0.06
    ιαÏĤ
    -0.06
    /goto
    -0.06
    alfa
    -0.06
    POSITIVE LOGITS
    :frame
    0.07
    blocks
    0.07
    webtoken
    0.07
     Nagar
    0.07
    ilk
    0.07
    PageIndex
    0.07
    Led
    0.06
    oust
    0.06
    éal
    0.06
    classic
    0.06
    Activations Density 0.007%

    No Known Activations