© 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. 15-LLAMASCOPE-RES-131K
    11. 61832
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or relationships

    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
     vs
    -0.06
     Cortex
    -0.06
     Strong
    -0.06
    iones
    -0.06
    jong
    -0.06
     Dig
    -0.05
    ivar
    -0.05
     Slater
    -0.05
    usterity
    -0.05
    ora
    -0.05
    POSITIVE LOGITS
     اØ
    0.08
    .metro
    0.07
    ãĤ¦ãĥĪ
    0.07
    wnd
    0.07
    avigate
    0.07
    itemid
    0.07
    ?action
    0.06
    aska
    0.06
    Flo
    0.06
    gren
    0.06
    Activations Density 0.089%

    No Known Activations