© 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. 126445
    Prev
    Next
    INDEX
    Explanations

    occurrences of underscores and variable references 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
     Erotische
    -0.07
    edia
    -0.07
    اÙĨد
    -0.07
    -svg
    -0.07
    æ´²
    -0.06
    psilon
    -0.06
    anki
    -0.06
    å
    -0.06
    defaults
    -0.06
    ixo
    -0.06
    POSITIVE LOGITS
     pseud
    0.07
    arak
    0.06
     discern
    0.06
    occo
    0.06
    816
    0.06
    assy
    0.06
    ing
    0.05
    raison
    0.05
     OL
    0.05
    etus
    0.05
    Activations Density 0.005%

    No Known Activations