INDEX

Explanations

occurrences of punctuation and formatting during explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

arra

-0.19

ucc

-0.15

ab

-0.14

etCode

-0.14

uen

-0.14

.toByteArray

-0.13

sumer

-0.13

abbo

-0.13

itize

-0.13

utton

-0.13

POSITIVE LOGITS

acre

0.16

acos

0.16

ovsky

0.15

-aos

0.15

atÃ¶r

0.14

 Ø£Ø¹ÙĦØ§Ùħ

0.14

inez

0.13

RIPT

0.13

 Overrides

0.13

Activations Density 0.783%

occurrences of punctuation and formatting during explanations

No Comments

No Known Activations