© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40180
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and advocacy groups focused on child welfare

    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
     Maryland
    -0.11
     Pennsylvania
    -0.10
     Massachusetts
    -0.10
     Virginia
    -0.08
     Texas
    -0.08
     VA
    -0.08
     Philadelphia
    -0.07
     Baltimore
    -0.07
    altimore
    -0.07
    Virginia
    -0.07
    POSITIVE LOGITS
     Auckland
    0.20
     NZ
    0.19
    NZ
    0.18
    .nz
    0.17
     Zealand
    0.15
     nz
    0.15
    nz
    0.14
    uckland
    0.14
     Ki
    0.13
     ki
    0.13
    Activations Density 0.145%

    No Known Activations