© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56337
    Prev
    Next
    INDEX
    Explanations

    references to circular shapes or formations

    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
    .UnitTesting
    -0.07
     Rarity
    -0.07
    /crypto
    -0.07
    _TUN
    -0.07
    ters
    -0.07
    ÑģÑĤиÑĩ
    -0.07
    lund
    -0.07
    tiv
    -0.07
    igr
    -0.07
    mscorlib
    -0.07
    POSITIVE LOGITS
    -eyed
    0.10
    (circle
    0.09
    -circle
    0.09
    овоÑĢ
    0.08
     circumference
    0.08
    uate
    0.08
    åľĪ
    0.07
     tròn
    0.07
    -loop
    0.07
    wald
    0.07
    Activations Density 0.014%

    No Known Activations