INDEX

Explanations

programming-related exceptions and class reflection elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

adr

-0.16

defs

-0.15

umen

-0.15

ÙĦÛĮÙĦ

-0.15

Æ°Æ¡i

-0.14

oro

-0.14

arker

-0.14

èĤ¥

-0.14

ÑĸÐ´Ð¾Ð¼

-0.14

ikut

-0.14

POSITIVE LOGITS

 èĳ

0.15

haven

0.14

tem

0.14

Įĵ

0.14

á»¥

0.14

 ages

0.14

gger

0.14

ulace

0.13

acco

0.13

Activations Density 0.072%

programming-related exceptions and class reflection elements

No Comments

No Known Activations