© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61924
    Prev
    Next
    INDEX
    Explanations

    instructions or commands related to entering data

    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
    ales
    -0.06
    ira
    -0.06
    £
    -0.06
    ener
    -0.06
    gn
    -0.06
     Dust
    -0.06
    blink
    -0.06
    iger
    -0.06
    ijo
    -0.06
    bl
    -0.06
    POSITIVE LOGITS
     ØŃاضر
    0.07
    prising
    0.07
    ãĤĤãĤĬ
    0.07
    uite
    0.07
    prises
    0.07
    ynamo
    0.07
    央
    0.07
    .peer
    0.07
    upal
    0.07
    UGINS
    0.06
    Activations Density 0.011%

    No Known Activations