© 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. 76236
    Prev
    Next
    INDEX
    Explanations

    instances of the word "posted" indicating entries or updates

    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
     Writes
    -0.07
    isse
    -0.07
     Sinai
    -0.06
    ãĥ³ãĥģ
    -0.06
     writ
    -0.06
    venes
    -0.06
     Erotische
    -0.06
     dept
    -0.06
    á»ijc
    -0.06
    λÏĮ
    -0.06
    POSITIVE LOGITS
    pons
    0.07
    611
    0.07
    bara
    0.06
    alian
    0.06
    ella
    0.06
     Cly
    0.06
    -overlay
    0.06
    itr
    0.06
    odata
    0.06
    phem
    0.06
    Activations Density 0.001%

    No Known Activations