INDEX

Explanations

occurrences of lines and line numbers in a programming context

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

 eldre

-0.15

 Bond

-0.14

 paging

-0.14

essim

-0.14

acket

-0.14

rown

-0.14

ifen

-0.13

 Gang

-0.13

ML

-0.13

ksen

-0.13

POSITIVE LOGITS

 Verde

0.15

zcze

0.14

Loc

0.14

tuy

0.14

si

0.14

ÙģÙĤ

0.14

gfx

0.14

arget

0.13

 atol

0.13

fin

0.13

Activations Density 0.006%

occurrences of lines and line numbers in a programming context

No Comments

No Known Activations