© 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. 76382
    Prev
    Next
    INDEX
    Explanations

    references to collective groups of people, particularly focusing on the public or community context

    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
    borough
    -0.08
    opaque
    -0.08
    .Forms
    -0.08
    ]={↵
    -0.07
    iliar
    -0.07
    ç±į
    -0.07
    ilen
    -0.07
     ìĥĪê¸Ģ
    -0.07
    UDA
    -0.07
    wiÄħ
    -0.07
    POSITIVE LOGITS
     lay
    0.07
    è¼
    0.07
     hum
    0.07
     humans
    0.07
    stood
    0.07
     sat
    0.07
     humanity
    0.06
    ench
    0.06
     mankind
    0.06
    sembled
    0.06
    Activations Density 0.007%

    No Known Activations