© 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. 129106
    Prev
    Next
    INDEX
    Explanations

    concepts related to firearms and their features

    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
    /stretch
    -0.07
     swords
    -0.07
    ระ
    -0.07
    alet
    -0.06
     gad
    -0.06
    ledo
    -0.06
     padd
    -0.06
    кÑĸн
    -0.06
    iverz
    -0.06
    afe
    -0.06
    POSITIVE LOGITS
     targets
    0.10
     targeting
    0.10
     target
    0.09
     Targets
    0.09
    -target
    0.09
     accuracy
    0.09
     shots
    0.08
     firing
    0.08
     shot
    0.08
    target
    0.08
    Activations Density 0.017%

    No Known Activations