© 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. 118477
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional scenarios or alternatives

    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
    ï¸
    -0.08
    еÑĢж
    -0.06
    agger
    -0.06
    ÑĢÑĥж
    -0.06
     hers
    -0.06
    _interval
    -0.06
    anza
    -0.06
    ayo
    -0.06
    ÑģÑı
    -0.06
    atat
    -0.05
    POSITIVE LOGITS
     other
    0.36
     similar
    0.28
    other
    0.27
     autres
    0.26
    åħ¶ä»ĸ
    0.24
     Other
    0.23
    -other
    0.23
     OTHER
    0.23
     otras
    0.23
    _other
    0.23
    Activations Density 0.228%

    No Known Activations