© 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. 17-LLAMASCOPE-RES-131K
    11. 29507
    Prev
    Next
    INDEX
    Explanations

    references to programming rules and formatting guidelines

    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
    punk
    -0.06
     Rift
    -0.06
    lick
    -0.06
    pard
    -0.06
    athed
    -0.06
    atan
    -0.06
    ãĥ³ãĥĦ
    -0.06
    EATURE
    -0.06
    -append
    -0.06
    ritch
    -0.06
    POSITIVE LOGITS
     CWE
    0.08
     rule
    0.08
     violations
    0.08
     violation
    0.08
    tro
    0.07
    axe
    0.07
    .issue
    0.07
    isse
    0.07
     remed
    0.07
     viol
    0.07
    Activations Density 0.007%

    No Known Activations