© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16069
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of projects and structures, particularly those involving lists and organization

    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
     Roots
    -0.06
     everyone
    -0.06
     zat
    -0.06
    id
    -0.06
    un
    -0.06
     people
    -0.06
     Id
    -0.06
    idi
    -0.06
     tun
    -0.06
    RAP
    -0.06
    POSITIVE LOGITS
     Incontri
    0.07
    gatsby
    0.07
    ichni
    0.07
    ги
    0.07
    iÅŁ
    0.07
    uding
    0.07
    вид
    0.07
    æľºåħ³
    0.07
    avn
    0.07
     Sesso
    0.07
    Activations Density 0.005%

    No Known Activations