© 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. 125316
    Prev
    Next
    INDEX
    Explanations

    requests or invitations for feedback or interaction

    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
    æķ·
    -0.08
    izin
    -0.06
    -law
    -0.06
    875
    -0.06
    ussen
    -0.06
    uku
    -0.06
     büny
    -0.06
    oked
    -0.06
    /pub
    -0.06
    ìĿ´ìĬĪ
    -0.06
    POSITIVE LOGITS
     us
    0.08
     Babe
    0.07
     Reb
    0.06
    imetype
    0.06
    hec
    0.06
    arya
    0.06
     Doctor
    0.06
    383
    0.06
    ãĥ¼ãĥĨ
    0.06
    tu
    0.06
    Activations Density 0.005%

    No Known Activations