© 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. 125500
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions, meetings, and collaborative planning efforts

    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
    uries
    -0.08
    istrovstvÃŃ
    -0.07
    WidthSpace
    -0.07
     Moreno
    -0.07
    íĺģ
    -0.07
    _sqrt
    -0.06
    .RunWith
    -0.06
    æŁ³
    -0.06
    ANGLES
    -0.06
    SCALL
    -0.06
    POSITIVE LOGITS
     discuss
    0.12
     discussing
    0.12
     discussion
    0.12
     discussed
    0.11
     discusses
    0.10
    discussion
    0.08
     discussions
    0.08
     review
    0.08
     обÑģ
    0.07
    Discuss
    0.07
    Activations Density 0.032%

    No Known Activations