© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84023
    Prev
    Next
    INDEX
    Explanations

    references to military themes or 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
    vez
    -0.08
    TERNAL
    -0.08
    ieties
    -0.08
    jeta
    -0.07
    warts
    -0.07
    itters
    -0.07
    bsolute
    -0.07
    istrovstvÃŃ
    -0.07
    onte
    -0.07
    erer
    -0.07
    POSITIVE LOGITS
    itles
    0.06
    ten
    0.06
    oux
    0.06
     Mil
    0.06
    uary
    0.06
    ainment
    0.05
     Beg
    0.05
    ory
    0.05
     Arn
    0.05
    unami
    0.05
    Activations Density 0.005%

    No Known Activations