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. 17-LLAMASCOPE-RES-131K
    6. 16342
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords in 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
    Ĥæķ°
    -0.08
    oret
    -0.08
    ICI
    -0.07
    664
    -0.07
    WithOptions
    -0.07
     nonatomic
    -0.07
    ForRow
    -0.07
    ãĥ¯ãĥ¼
    -0.07
    fo
    -0.07
    ĶåĽŀ
    -0.06
    POSITIVE LOGITS
    hpp
    0.06
    ÑĥÑĢÑĥ
    0.06
    ewed
    0.06
    iglia
    0.06
    ÅĻes
    0.06
    otor
    0.05
    xbd
    0.05
    raig
    0.05
    Âłmi
    0.05
    unch
    0.05
    Activations Density 0.013%

    No Known Activations