© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98654
    Prev
    Next
    INDEX
    Explanations

    contexts related to instructions, requests, or procedures

    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
    ael
    -0.07
    izoph
    -0.06
    vir
    -0.06
    issors
    -0.06
    коÑĤ
    -0.06
     topics
    -0.06
     Apprec
    -0.06
     havoc
    -0.06
    виÑĩай
    -0.06
    ози
    -0.05
    POSITIVE LOGITS
     rid
    0.07
    igmat
    0.07
    èĪį
    0.06
    metatable
    0.06
    ucc
    0.06
    Jets
    0.06
    /send
    0.06
    APTER
    0.06
    iator
    0.06
    Äįer
    0.06
    Activations Density 0.047%

    No Known Activations