© 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. 22-LLAMASCOPE-RES-131K
    11. 4286
    Prev
    Next
    INDEX
    Explanations

    details about familial relationships and events surrounding childbirth

    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
     voks
    -0.08
    .scalablytyped
    -0.08
    thouse
    -0.07
     deren
    -0.07
    .MixedReality
    -0.07
    TestCategory
    -0.07
    SGlobal
    -0.07
    мага
    -0.07
    abler
    -0.07
    âĢĮâĢĮ
    -0.06
    POSITIVE LOGITS
     team
    0.15
     couple
    0.14
     they
    0.14
     group
    0.12
     pair
    0.12
     duo
    0.11
     family
    0.11
     trio
    0.11
     authors
    0.11
    team
    0.11
    Activations Density 0.106%

    No Known Activations