© 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. 118980
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to borders and solid styles

    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
    ARP
    -0.08
    apon
    -0.08
    dain
    -0.07
    InvalidOperationException
    -0.07
    ToFit
    -0.07
    elsing
    -0.07
    duino
    -0.07
     bÅĻez
    -0.07
    866
    -0.07
    ayne
    -0.07
    POSITIVE LOGITS
     Beard
    0.07
     light
    0.06
     Jak
    0.06
    igm
    0.06
    azer
    0.06
     Reflex
    0.06
    ombat
    0.06
    imit
    0.06
    l
    0.06
    p
    0.05
    Activations Density 0.005%

    No Known Activations