© 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. 126784
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical standards and responsibility in society

    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
    ets
    -0.07
    homes
    -0.06
    emb
    -0.06
    ingles
    -0.06
    osi
    -0.06
     ÑģебÑı
    -0.06
    stal
    -0.06
    ETS
    -0.06
    vim
    -0.06
    zi
    -0.06
    POSITIVE LOGITS
    arez
    0.07
    .jquery
    0.07
    yne
    0.06
    lander
    0.06
    onet
    0.06
     Truy
    0.06
    nock
    0.06
    atto
    0.06
    Hey
    0.06
    ]=>
    0.06
    Activations Density 0.036%

    No Known Activations