© 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. 9-LLAMASCOPE-RES-131K
    11. 95907
    Prev
    Next
    INDEX
    Explanations

    references to photography and capturing images

    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
    _plural
    -0.07
    drawing
    -0.07
    rand
    -0.07
    aph
    -0.07
     est
    -0.06
    vely
    -0.06
    ahoo
    -0.06
    agas
    -0.06
    land
    -0.06
     INTERRUPTION
    -0.06
    POSITIVE LOGITS
    .struts
    0.07
    ADR
    0.06
     Bowen
    0.06
    .Pattern
    0.06
    anine
    0.06
    udit
    0.06
     Mö
    0.06
    ÑŁ
    0.06
     Roose
    0.06
    plode
    0.06
    Activations Density 0.022%

    No Known Activations