© 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. 5-LLAMASCOPE-RES-131K
    11. 125887
    Prev
    Next
    INDEX
    Explanations

    semicolons and import statements 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
    ez
    -0.07
    aign
    -0.06
    jec
    -0.06
    tre
    -0.06
    oub
    -0.06
    ¶ļ
    -0.06
    ÅĤ
    -0.06
    agne
    -0.06
     Barcl
    -0.06
    ceae
    -0.06
    POSITIVE LOGITS
    cka
    0.07
    387
    0.07
    olin
    0.07
    isci
    0.06
    ogan
    0.06
     Uno
    0.06
    amer
    0.06
    μμ
    0.06
    Multiplicity
    0.06
    osy
    0.06
    Activations Density 0.002%

    No Known Activations