© 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. 124911
    Prev
    Next
    INDEX
    Explanations

    objects and significant actions related to physical interactions

    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
    imary
    -0.07
    dfa
    -0.06
    988
    -0.06
    quot
    -0.06
    inel
    -0.06
    بÙĩ
    -0.06
    821
    -0.06
    aise
    -0.06
    SEM
    -0.06
    998
    -0.06
    POSITIVE LOGITS
     then
    0.08
    then
    0.07
     and
    0.07
    .then
    0.07
    uz
    0.06
    erson
    0.06
     Then
    0.06
    Then
    0.06
    uds
    0.06
    ittle
    0.06
    Activations Density 0.025%

    No Known Activations