© 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. 15-LLAMASCOPE-RES-131K
    11. 27160
    Prev
    Next
    INDEX
    Explanations

    instances of submissions, applications, and their related processes

    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
    487
    -0.06
    -devel
    -0.06
     various
    -0.05
    laus
    -0.05
     Ive
    -0.05
     Apostle
    -0.05
    appy
    -0.05
     called
    -0.05
    ablish
    -0.05
    .so
    -0.05
    POSITIVE LOGITS
    akedown
    0.08
    ampa
    0.07
     sonst
    0.07
    endale
    0.07
    DataURL
    0.07
    Calibri
    0.07
     Marino
    0.07
     must
    0.07
    Appending
    0.07
    won
    0.07
    Activations Density 0.014%

    No Known Activations