© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    details related to food and beverage events or offerings

    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
    èĨ
    -0.15
     Irvine
    -0.14
    æ²Ī
    -0.14
    ãĤ¹ãĥĿ
    -0.14
    Holiday
    -0.14
    ureen
    -0.13
     доÑĢ
    -0.13
     Holiday
    -0.13
     Ring
    -0.13
    almart
    -0.13
    POSITIVE LOGITS
     Vaults
    0.18
     instagram
    0.18
     interiors
    0.18
     gin
    0.17
    GIN
    0.17
    Inject
    0.17
    å±
    0.17
     ICMP
    0.16
    ÌĨ
    0.15
     Byron
    0.15
    Activations Density 0.298%

    No Known Activations