© 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. 17-LLAMASCOPE-RES-131K
    11. 17257
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate criminal acts or safety concerns related to gang activity

    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
    ÑĤÑİ
    -0.08
    pga
    -0.07
    ICH
    -0.07
     cach
    -0.07
    olding
    -0.07
    åĪĢ
    -0.07
    .construct
    -0.07
    NSS
    -0.07
    Ïĥί
    -0.07
    HUD
    -0.07
    POSITIVE LOGITS
    igen
    0.07
    269
    0.06
    617
    0.06
    akes
    0.06
     dys
    0.06
     Timber
    0.06
    logs
    0.05
     slur
    0.05
    akening
    0.05
     alien
    0.05
    Activations Density 0.009%

    No Known Activations