INDEX

Explanations

programming-related terms and structures within code

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

DTV

-0.14

JNI

-0.13

Dup

-0.13

/epl

-0.13

ä½ĵèĤ²

-0.13

Ã¡nh

-0.13

Bri

-0.13

quelle

-0.13

IFA

-0.13

deaux

-0.13

POSITIVE LOGITS

0.15

	fflush

0.15

aram

0.14

0.13

 general

0.13

 simply

0.13

 frau

0.13

 [âĢ¦]↵↵

0.13

 Friedman

0.13

Activations Density 0.334%

programming-related terms and structures within code

No Comments

No Known Activations