INDEX

Explanations

code and programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 gang

-0.14

aux

-0.14

 __("

-0.14

illac

-0.13

OLON

-0.13

iards

-0.13

iod

-0.13

nl

-0.13

ngth

-0.13

ief

-0.13

POSITIVE LOGITS

ucer

0.15

anj

0.15

Ø±ÙĬØ·

0.14

/WebAPI

0.14

oor

0.14

aal

0.14

irth

0.14

 abstract

0.14

owa

0.14

Activations Density 0.032%

code and programming-related terms

No Comments

No Known Activations