INDEX

Explanations

code-related preprocessor directives and structural elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ãĥ¼ãĥ©

-0.17

ayo

-0.16

odo

-0.15

dam

-0.15

ingen

-0.15

age

-0.15

ajo

-0.14

 Alive

-0.14

eller

-0.14

 Ipsum

-0.14

POSITIVE LOGITS

canf

0.17

sing

0.16

opard

0.15

¥Ĳ

0.14

zimmer

0.14

lue

0.14

ÅĤug

0.14

stial

0.14

Å¡Å¥

0.14

ANI

0.14

Activations Density 0.001%

code-related preprocessor directives and structural elements

No Comments

No Known Activations