INDEX

Explanations

programming-related terms and code structures

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

ëª°

-0.17

Î´Î¯

-0.16

stown

-0.15

okable

-0.15

iffin

-0.14

=yes

-0.14

arkan

-0.14

å·¥

-0.14

-0.13

ogle

-0.13

POSITIVE LOGITS

 CURLOPT

0.19

("

0.18

("_

0.18

 offsetof

0.18

.scalablytyped

0.18

('_

0.16

('

0.15

 nameof

0.15

_("

0.15

byname

0.15

Activations Density 0.110%

programming-related terms and code structures

No Comments

No Known Activations