© 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. 75118
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or quotations

    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
    opup
    -0.08
    èo
    -0.08
    .intellij
    -0.08
    ÃŃk
    -0.07
    ãĥªãĤ¢
    -0.07
    еÑĢи
    -0.07
    ushi
    -0.07
    ãĤ¾
    -0.07
    usk
    -0.07
    .enumer
    -0.07
    POSITIVE LOGITS
     sometimes
    0.06
     I
    0.06
    quia
    0.06
     there
    0.06
    irim
    0.06
    unic
    0.05
    ÅĽmy
    0.05
    sometimes
    0.05
     infant
    0.05
     Moor
    0.05
    Activations Density 0.021%

    No Known Activations