INDEX

Explanations

symbols and formatting characters used in code, particularly in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uyá»ĩt

-0.19

ence

-0.17

/or

-0.17

enu

-0.17

ese

-0.16

ric

-0.16

ifer

-0.16

entially

-0.15

lix

-0.15

ract

-0.15

POSITIVE LOGITS

::|

0.19

.scalablytyped

0.18

.|

0.17

.SIG

0.17

uju

0.15

UnderTest

0.15

vette

0.15

ulumi

0.14

 colspan

0.14

ocale

0.14

Activations Density 0.067%

symbols and formatting characters used in code, particularly in programming or markup languages

No Comments

No Known Activations