© 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. 87131
    Prev
    Next
    INDEX
    Explanations

    annotations or comments in code

    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
    764
    -0.06
     Zot
    -0.06
    esen
    -0.06
    Ïįν
    -0.06
    alink
    -0.06
    rozen
    -0.06
    coni
    -0.06
    andest
    -0.06
    364
    -0.05
    juven
    -0.05
    POSITIVE LOGITS
    à¸ļà¸Ħ
    0.09
    teÅŁ
    0.07
    .scalablytyped
    0.07
    ãĥ³ãĤ°ãĥ«
    0.07
     Franc
    0.06
    kowski
    0.06
     weg
    0.06
    arb
    0.06
     Elliot
    0.06
    onga
    0.06
    Activations Density 0.002%

    No Known Activations