Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5269
    Prev
    Next
    INDEX
    Explanations

    words related to physical strength or force

    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
    ium
    -0.07
    teil
    -0.07
    angelo
    -0.07
     McGu
    -0.07
    emente
    -0.07
    _BEGIN
    -0.06
    çĭIJ
    -0.06
     EVT
    -0.06
    andard
    -0.06
    hesive
    -0.06
    POSITIVE LOGITS
     kn
    0.08
    appa
    0.08
    otted
    0.08
    uckles
    0.07
    uckle
    0.07
    s
    0.07
    rade
    0.07
    uck
    0.07
    obby
    0.07
    uts
    0.06
    Activations Density 0.004%

    No Known Activations