© 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. 83098
    Prev
    Next
    INDEX
    Explanations

    words related to military victories or conquests

    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
    ãĥ¼ãĥIJ
    -0.06
     guild
    -0.06
    getti
    -0.06
     King
    -0.06
    encodeURIComponent
    -0.05
    aÄį
    -0.05
    enek
    -0.05
    bakan
    -0.05
    ileo
    -0.05
     competition
    -0.05
    POSITIVE LOGITS
     Hindered
    0.08
    ulen
    0.07
    intage
    0.07
    onu
    0.07
    èļ
    0.07
    ÑħодиÑĤÑĮ
    0.07
    .jasper
    0.07
    ãĥ
    0.07
     bì
    0.07
    stellen
    0.07
    Activations Density 0.000%

    No Known Activations