INDEX

Explanations

punctuation and sentence boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ELS

-0.15

min

-0.15

UME

-0.14

mins

-0.14

mot

-0.14

Ã³m

-0.14

elles

-0.13

amax

-0.13

OF

-0.13

.jobs

-0.13

POSITIVE LOGITS

opsis

0.15

_RETRY

0.15

Ð¿Ð¾Ð²ÑĸÐ´

0.15

ãĥ¼ãĥĦ

0.14

ingle

0.14

orida

0.14

ãĤ¹ãĥĪ

0.14

uplic

0.14

ben

0.14

beck

0.14

Activations Density 0.568%

punctuation and sentence boundaries

No Comments

No Known Activations