© 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. 56358
    Prev
    Next
    INDEX
    Explanations

    names or initials associated with individuals

    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
    _________________↵↵
    -0.08
     zdrav
    -0.08
     имÑĥ
    -0.08
    ãĥ¬ãĥĥãĥĪ
    -0.08
    лÑıд
    -0.08
    "+"
    -0.08
     зави
    -0.08
    spender
    -0.07
    alsex
    -0.07
    lanma
    -0.07
    POSITIVE LOGITS
    j
    0.07
    je
    0.06
    IVEN
    0.06
     forgot
    0.06
    jer
    0.06
     magician
    0.06
    Question
    0.06
    1
    0.05
    enburg
    0.05
    ier
    0.05
    Activations Density 0.009%

    No Known Activations