© 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. 55892
    Prev
    Next
    INDEX
    Explanations

    repeated phrasing and structure that convey similarity

    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
    YNAM
    -0.07
    íķĻ기
    -0.07
    IAS
    -0.07
    érc
    -0.07
    =__
    -0.07
    ointed
    -0.06
    ocalypse
    -0.06
    imir
    -0.06
    kontakte
    -0.06
    /wiki
    -0.06
    POSITIVE LOGITS
     importantly
    0.10
    heim
    0.06
    Pi
    0.06
    ADB
    0.06
    ames
    0.06
    azi
    0.06
    å¸
    0.05
     Prepared
    0.05
     æĺ
    0.05
     important
    0.05
    Activations Density 0.004%

    No Known Activations