© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94450
    Prev
    Next
    INDEX
    Explanations

    phrases related to influence and contribution in sociopolitical contexts

    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
    outil
    -0.07
    asaki
    -0.07
    rika
    -0.07
    ohana
    -0.07
    ifold
    -0.07
    inho
    -0.07
    adamente
    -0.07
     UObject
    -0.07
     (::
    -0.07
    phia
    -0.07
    POSITIVE LOGITS
     role
    0.13
     Role
    0.11
    role
    0.10
    Role
    0.10
     contribution
    0.10
     ROLE
    0.09
     roles
    0.09
    (role
    0.09
     ÑĢолÑĮ
    0.08
     contributions
    0.08
    Activations Density 0.030%

    No Known Activations