INDEX

Explanations

programming language keywords and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

pou

-0.14

ãĤĴè¦ĭãĤĭ

-0.13

empo

-0.13

rz

-0.13

ÑģÑıÑĤ

-0.13

çĶ³

-0.13

\Base

-0.13

-fly

-0.13

 Sens

-0.13

hip

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

inic

0.16

Ã©ri

0.15

$LANG

0.15

$MESS

0.14

akin

0.14

áº·n

0.14

roe

0.14

icher

0.14

 Svens

0.14

Activations Density 0.011%

programming language keywords and symbols

No Comments

No Known Activations