© 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. 24-LLAMASCOPE-RES-32K
    11. 15465
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those associated with dates, prices, or ratings in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thic
    -0.15
    abbo
    -0.14
    ennifer
    -0.14
    assandra
    -0.14
    goog
    -0.14
     Alfred
    -0.14
    MESS
    -0.13
     å¨
    -0.13
    857
    -0.13
    ooks
    -0.13
    POSITIVE LOGITS
     PARTICULAR
    0.15
    yer
    0.15
    kre
    0.15
    Ñģклад
    0.14
    /MPL
    0.14
    OTES
    0.14
    yers
    0.14
    (Android
    0.14
    Õ¡
    0.14
    /UIKit
    0.14
    Activations Density 0.060%

    No Known Activations