© 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. 76063
    Prev
    Next
    INDEX
    Explanations

    elements related to social interactions and emotional responses

    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
    rale
    -0.07
    udit
    -0.07
    енноÑģÑĤÑĮ
    -0.07
    [$_
    -0.06
    ös
    -0.06
    ctor
    -0.06
    ilitation
    -0.06
    PACE
    -0.06
    .ZERO
    -0.06
    มà¸Ĥ
    -0.06
    POSITIVE LOGITS
    Ư
    0.07
    raki
    0.07
    евеÑĢ
    0.06
    eydi
    0.06
    AIT
    0.06
    dyn
    0.06
     Pillow
    0.06
    $t
    0.06
    веÑģÑĤ
    0.06
    |=↵
    0.06
    Activations Density 0.157%

    No Known Activations