© 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. 60827
    Prev
    Next
    INDEX
    Explanations

    conditional statements indicating prerequisites or requirements

    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
    org
    -0.06
    also
    -0.06
    all
    -0.06
    aci
    -0.05
    amp
    -0.05
     systemic
    -0.05
    com
    -0.05
    ihn
    -0.05
    aylor
    -0.05
    ana
    -0.05
    POSITIVE LOGITS
    éģĩ
    0.10
     encount
    0.09
     encounter
    0.08
     encountering
    0.08
     situation
    0.07
    olla
    0.07
     encountered
    0.07
    eyse
    0.07
    ¢°
    0.07
    notice
    0.07
    Activations Density 0.018%

    No Known Activations