© 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. 83055
    Prev
    Next
    INDEX
    Explanations

    domain suffixes associated with educational and informational resources

    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
    .chapter
    -0.07
    ei
    -0.07
     Hud
    -0.07
    endon
    -0.07
    ayd
    -0.06
    geries
    -0.06
    ÅĤÄħ
    -0.06
    atus
    -0.06
    llib
    -0.06
    lsx
    -0.06
    POSITIVE LOGITS
    irs
    0.07
    .scalablytyped
    0.06
     UK
    0.06
     USA
    0.06
    hte
    0.06
    UK
    0.05
    werk
    0.05
     Hopkins
    0.05
     fe
    0.05
     Jeb
    0.05
    Activations Density 0.011%

    No Known Activations