INDEX

Explanations

structures that represent code or programming constructs

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

alo

-0.16

idge

-0.15

§

-0.15

icia

-0.15

isia

-0.14

 Î±ÏħÏĦÎ®

-0.14

ivia

-0.13

.ar

-0.13

ÑĸÑĩ

-0.13

usk

-0.13

POSITIVE LOGITS

lag

0.18

nad

0.15

ebb

0.15

iyel

0.13

 combinations

0.13

ftime

0.13

_ib

0.13

isine

0.13

Fmt

0.13

ftware

0.13

Activations Density 0.142%

structures that represent code or programming constructs

No Comments

No Known Activations