INDEX

Explanations

indicators of time and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Sortable

-0.15

 WCHAR

-0.14

 pseud

-0.14

Ð»Ð°Ð±

-0.14

lia

-0.14

 Bilim

-0.14

Ã¤nn

-0.13

ldb

-0.13

.stroke

-0.13

OLEAN

-0.13

POSITIVE LOGITS

advanced

0.16

 advanced

0.15

elly

0.14

standen

0.14

Ware

0.14

LIKELY

0.14

fare

0.14

ê°ģ

0.14

 bach

0.14

achen

0.13

Activations Density 0.028%

indicators of time and dates

No Comments

No Known Activations