INDEX

Explanations

function calls related to string manipulation, particularly searching and indexing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

zeÅĦ

-0.16

ulet

-0.16

Ã¶r

-0.15

igh

-0.14

egas

-0.14

Ĥ¹

-0.14

ttp

-0.14

	throws

-0.14

axy

-0.14

iÄĩ

-0.14

POSITIVE LOGITS

erland

0.18

arth

0.17

áº¡n

0.15

 namedtuple

0.14

ains

0.14

 Lawn

0.13

kaar

0.13

Ð°ÑĢÐ°Ð½

0.13

cop

0.13

PIO

0.13

Activations Density 0.032%

function calls related to string manipulation, particularly searching and indexing

No Comments

No Known Activations