© 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. 119370
    Prev
    Next
    INDEX
    Explanations

    occurrences of structuring elements and remarks in legal or formal documents

    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
    arch
    -0.07
     Pru
    -0.06
    _hop
    -0.06
     Dame
    -0.06
    eniable
    -0.06
    els
    -0.06
    ARCH
    -0.06
     doma
    -0.06
    à¹Ģหล
    -0.06
    ela
    -0.06
    POSITIVE LOGITS
    ivor
    0.07
    รร
    0.06
    imbus
    0.06
    engo
    0.06
    frei
    0.06
    alars
    0.06
    æ½®
    0.06
     duplicate
    0.06
     note
    0.06
    çĤī
    0.06
    Activations Density 0.005%

    No Known Activations