© 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. 71447
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers associated with technical specifications

    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
    olec
    -0.08
    Ý
    -0.07
    NEXT
    -0.07
    heet
    -0.07
     (++
    -0.06
    pNet
    -0.06
    inker
    -0.06
    vae
    -0.06
    ÏĩÏĮ
    -0.06
    DAQ
    -0.06
    POSITIVE LOGITS
     Bernstein
    0.07
    rike
    0.06
    áno
    0.06
    åł¡
    0.06
    thood
    0.06
     Huff
    0.06
     Chang
    0.06
    UDO
    0.06
    ãĥ¼ãĥį
    0.06
     Along
    0.05
    Activations Density 0.026%

    No Known Activations