© 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 EvalsExportsAPI 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. 29225
    Prev
    Next
    INDEX
    Explanations

    statements regarding brand identity and recognition

    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
    ee
    -0.06
     courtesy
    -0.06
     eff
    -0.06
     politically
    -0.05
     ph
    -0.05
     scientifically
    -0.05
     memor
    -0.05
     pit
    -0.05
    ingly
    -0.05
    (sys
    -0.05
    POSITIVE LOGITS
    ollo
    0.08
    Ñħодим
    0.08
    SetBranch
    0.08
    PROTO
    0.07
    ãi
    0.07
    azio
    0.07
    ãĥ©ãĤ¹
    0.07
    кÑĥп
    0.07
    éĩ
    0.07
    ãģªãĤĵãģł
    0.07
    Activations Density 0.000%

    No Known Activations