© 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. 15-LLAMASCOPE-RES-131K
    11. 27079
    Prev
    Next
    INDEX
    Explanations

    references to graphic violence and sexual content

    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
     Sky
    -0.06
    ench
    -0.06
    265
    -0.06
    oi
    -0.06
     %#
    -0.06
     sky
    -0.06
    245
    -0.06
    lle
    -0.06
    este
    -0.06
    ego
    -0.05
    POSITIVE LOGITS
    atoi
    0.07
    æľī人
    0.07
     solic
    0.07
    ÑģÑİ
    0.07
    atoon
    0.07
     Keystone
    0.07
    acam
    0.06
    ÑĦÑĦ
    0.06
    .Microsoft
    0.06
    èĪĪ
    0.06
    Activations Density 0.017%

    No Known Activations