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. 22-LLAMASCOPE-RES-131K
    6. 4391
    Prev
    Next
    INDEX
    Explanations

    technical commands and instructions related to Docker

    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
     subs
    -0.06
    -Jun
    -0.06
     Bernstein
    -0.06
    彦
    -0.06
    IMUM
    -0.05
    imal
    -0.05
    yu
    -0.05
    isch
    -0.05
    esch
    -0.05
    /pl
    -0.05
    POSITIVE LOGITS
     volumes
    0.09
    ainer
    0.08
    -volume
    0.08
    .scalablytyped
    0.08
    ihan
    0.07
     Stick
    0.07
     volume
    0.07
    mayan
    0.07
    ,copy
    0.07
    ieux
    0.07
    Activations Density 0.003%

    No Known Activations