© 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. 118620
    Prev
    Next
    INDEX
    Explanations

    references to military lifestyles and duties

    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
    åłĤ
    -0.08
    erna
    -0.07
    adele
    -0.07
    assed
    -0.07
    arial
    -0.07
    oger
    -0.07
    ysqli
    -0.07
    assium
    -0.07
    erno
    -0.07
    ëĮĢë¡ľ
    -0.06
    POSITIVE LOGITS
     away
    0.08
     travel
    0.07
    away
    0.07
    SingleNode
    0.07
     Away
    0.07
    atus
    0.07
     apart
    0.07
    -away
    0.06
    oux
    0.06
     leave
    0.06
    Activations Density 0.022%

    No Known Activations