© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126708
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimal outcomes or the concept of "best" in various contexts

    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
    allet
    -0.08
    landa
    -0.07
    aju
    -0.07
     double
    -0.07
    otts
    -0.06
    scal
    -0.06
    lico
    -0.06
     extra
    -0.06
    ầm
    -0.06
     easy
    -0.06
    POSITIVE LOGITS
     possible
    0.12
    possible
    0.11
     possibile
    0.11
     posible
    0.10
    Possible
    0.10
     Possible
    0.09
     possÃŃvel
    0.09
    _possible
    0.09
    åı¯èĥ½
    0.08
    iele
    0.08
    Activations Density 0.016%

    No Known Activations