© 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. 55642
    Prev
    Next
    INDEX
    Explanations

    instances of gatherings or collective actions

    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
    á
    -0.07
    aine
    -0.06
    isoft
    -0.06
    odon
    -0.06
    ica
    -0.05
     double
    -0.05
    entine
    -0.05
     past
    -0.05
     embedded
    -0.05
     Barnett
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.10
     Äijá»ĥ
    0.09
     أجÙĦ
    0.08
    _$_
    0.08
    .metamodel
    0.08
    ä¸Ģèµ·
    0.07
    ?}",
    0.07
     together
    0.07
    voor
    0.07
     вмеÑģÑĤе
    0.07
    Activations Density 0.031%

    No Known Activations