INDEX

Explanations

contextual phrases indicating specific offerings or opportunities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hyp

-0.15

Tow

-0.14

iz

-0.14

alan

-0.13

Je

-0.13

ize

-0.13

ãĥªãĤ¢

-0.13

levant

-0.13

arer

-0.13

ende

-0.13

POSITIVE LOGITS

igrams

0.15

journal

0.15

axon

0.15

ardin

0.15

çĪµ

0.15

 ç²

0.15

nings

0.14

pta

0.14

igram

0.14

 readers

0.14

Activations Density 0.163%

contextual phrases indicating specific offerings or opportunities

No Comments

No Known Activations