© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 26454
    Prev
    Next
    INDEX
    Explanations

    instances of military or organizational classifications and identifiers

    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
    nt
    -0.09
     Herman
    -0.06
    Ùħ
    -0.06
    -widgets
    -0.06
    548
    -0.06
    ?s
    -0.06
    xffffff
    -0.06
    ÃĤ
    -0.06
    ization
    -0.06
    “
    -0.06
    POSITIVE LOGITS
    amp
    0.12
    elper
    0.08
    erea
    0.08
    apos
    0.08
    imity
    0.08
    ฺ
    0.08
    quot
    0.08
    ÑĶм
    0.07
    emsp
    0.07
    conds
    0.07
    Activations Density 0.347%

    No Known Activations