© 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. 129213
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a group or category of 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
    yro
    -0.07
    mpar
    -0.06
    év
    -0.06
    _procs
    -0.06
     ÑĤеÑħ
    -0.06
    ekl
    -0.06
    atives
    -0.06
    _cli
    -0.06
     Miy
    -0.06
     '*',
    -0.06
    POSITIVE LOGITS
     who
    0.10
    who
    0.09
     же
    0.07
     sentiments
    0.07
    UBLE
    0.07
    ãģ¬
    0.07
    478
    0.07
    Who
    0.07
     Who
    0.06
     alone
    0.06
    Activations Density 0.013%

    No Known Activations