Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126509
    Prev
    Next
    INDEX
    Explanations

    phrases related to social engagement and recognition

    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
    315
    -0.07
    375
    -0.07
    \brief
    -0.07
    376
    -0.07
     steering
    -0.06
    SENS
    -0.06
    loha
    -0.06
     Milton
    -0.06
     Rogers
    -0.06
    OPSIS
    -0.06
    POSITIVE LOGITS
    tring
    0.07
    ::
    0.07
     matter
    0.06
    matter
    0.06
     Pey
    0.06
    .btnSave
    0.06
    liš
    0.06
     Matter
    0.06
    acades
    0.06
    odor
    0.06
    Activations Density 0.000%

    No Known Activations