© 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. 129088
    Prev
    Next
    INDEX
    Explanations

    references to military history and related commemorations

    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
    drv
    -0.09
    _compat
    -0.08
    subcategory
    -0.08
    ekil
    -0.08
    repos
    -0.07
    GetInt
    -0.07
    devil
    -0.07
    readcr
    -0.07
    ÛĮÛĮÙĨ
    -0.07
    sterol
    -0.07
    POSITIVE LOGITS
    ichage
    0.06
    oj
    0.06
    azing
    0.05
    анÑĤаж
    0.05
    owie
    0.05
     Castro
    0.05
    ãĥĥ
    0.05
    nard
    0.05
    ipp
    0.05
    ros
    0.05
    Activations Density 0.279%

    No Known Activations