© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3070
    Prev
    Next
    INDEX
    Explanations

    titles and elements of video games and their reviews

    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
    anton
    -0.08
    erif
    -0.07
    antro
    -0.07
    amina
    -0.07
    //{{
    -0.07
     Fus
    -0.06
    rai
    -0.06
     dy
    -0.06
    imb
    -0.06
    anal
    -0.06
    POSITIVE LOGITS
     Colleg
    0.07
    ominated
    0.06
    -themed
    0.06
    emies
    0.06
    коÑĢиÑģÑĤ
    0.06
     Gen
    0.06
    ξι
    0.06
    ounced
    0.06
    -inspired
    0.06
    reeze
    0.06
    Activations Density 0.022%

    No Known Activations