© 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. 125430
    Prev
    Next
    INDEX
    Explanations

    statements related to logical conditions and mathematical relationships

    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
    .scalablytyped
    -0.07
    CompleteListener
    -0.07
    ippi
    -0.07
     Zug
    -0.07
    ettel
    -0.07
     FieldType
    -0.06
    ikler
    -0.06
    066
    -0.06
    atra
    -0.06
     dil
    -0.06
    POSITIVE LOGITS
    TeX
    0.06
     already
    0.06
    koa
    0.06
    иÑĤе
    0.06
    åĪ«
    0.06
    anja
    0.06
    าะ
    0.06
    okus
    0.06
    _refl
    0.06
     MERCHANTABILITY
    0.06
    Activations Density 0.017%

    No Known Activations