© 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. 71575
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specific requirements or characteristics within a context

    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
    essler
    -0.08
    eya
    -0.07
    Reuse
    -0.07
    unch
    -0.07
    vinc
    -0.07
    conte
    -0.07
    phere
    -0.07
    اعÙĬ
    -0.07
    COMPARE
    -0.07
    ryo
    -0.07
    POSITIVE LOGITS
    ally
    0.08
    ity
    0.08
    /global
    0.07
    gger
    0.07
    ALLY
    0.07
     Barnett
    0.06
    ities
    0.06
    /local
    0.06
    s
    0.06
    ivi
    0.06
    Activations Density 0.018%

    No Known Activations