© 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. 119414
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and its variations in different contexts

    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
    _NEED
    -0.07
    émon
    -0.07
    pod
    -0.06
    ording
    -0.06
    ched
    -0.06
    iece
    -0.06
    .vm
    -0.06
    éĿ©
    -0.06
    unge
    -0.06
    á»iji
    -0.06
    POSITIVE LOGITS
    atori
    0.08
    дон
    0.07
    itag
    0.07
    ibel
    0.07
    237
    0.07
     meis
    0.06
    etry
    0.06
    ahy
    0.06
    ردد
    0.06
    ":"/
    0.06
    Activations Density 0.002%

    No Known Activations