© 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. 15-LLAMASCOPE-RES-131K
    6. 103675
    Prev
    Next
    INDEX
    Explanations

    specific syntactic structures or expressions in programming code

    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
    جÙĬ
    -0.07
    .ManyToMany
    -0.07
    enza
    -0.07
     št
    -0.07
    Ø¢Ùħ
    -0.07
    aines
    -0.06
     lif
    -0.06
    .scalablytyped
    -0.06
    _activ
    -0.06
     Blowjob
    -0.06
    POSITIVE LOGITS
    ominated
    0.06
    ropic
    0.06
     pend
    0.06
     Corn
    0.06
     false
    0.06
    _pb
    0.06
    xbc
    0.05
    idon
    0.05
    uhan
    0.05
     UObject
    0.05
    Activations Density 0.092%

    No Known Activations