INDEX

Explanations

open parentheses in code or data structures

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

-0.19

ç«ł

-0.16

aid

-0.16

Ãªn

-0.14

erez

-0.14

arel

-0.14

lo

-0.14

hil

-0.13

agne

-0.13

ensen

-0.13

POSITIVE LOGITS

?}",

0.16

IGO

0.15

Ä±za

0.15

lemn

0.15

 rare

0.15

Ð¾ÑĤÐ°

0.15

ziej

0.14

osate

0.14

Rare

0.14

apiro

0.14

Activations Density 0.041%

open parentheses in code or data structures

No Comments

No Known Activations