© 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. 17-LLAMASCOPE-RES-131K
    6. 76380
    Prev
    Next
    INDEX
    Explanations

    words related to permission or capability

    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
    ollo
    -0.06
    PEAR
    -0.06
    atable
    -0.06
    enne
    -0.06
     Regular
    -0.06
    меÑĤÑĮ
    -0.06
    CG
    -0.06
    bben
    -0.06
    поÑĢ
    -0.06
    ãĥªãĥ³ãĤ°
    -0.06
    POSITIVE LOGITS
    edd
    0.07
    oj
    0.06
    æŃ
    0.06
    geist
    0.06
     Webb
    0.06
    èµŀ
    0.06
     Dön
    0.06
     Buddy
    0.06
    Gas
    0.06
    icmp
    0.06
    Activations Density 0.004%

    No Known Activations