© 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. 74894
    Prev
    Next
    INDEX
    Explanations

    the name "Steve" in various contexts

    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
    ismet
    -0.08
     stolen
    -0.07
    loc
    -0.07
    rist
    -0.07
    éis
    -0.07
    xing
    -0.07
    nila
    -0.06
    edom
    -0.06
    UDGE
    -0.06
    nel
    -0.06
    POSITIVE LOGITS
    æĩ
    0.07
    otten
    0.07
     Zot
    0.07
    VEN
    0.06
    ÛĮز
    0.06
     importer
    0.06
    DTD
    0.06
    _VENDOR
    0.06
    quential
    0.06
     Wonder
    0.06
    Activations Density 0.016%

    No Known Activations