INDEX

Explanations

references to documentation and related files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

.lu

-0.15

elia

-0.15

 extra

-0.15

alloc

-0.15

ingly

-0.15

 Prest

-0.14

 perman

-0.14

 Alcohol

-0.14

éļĽ

-0.14

ikk

-0.14

POSITIVE LOGITS

abra

0.16

/Instruction

0.15

á»ĳt

0.15

han

0.14

fos

0.14

è¾ĵ

0.14

imit

0.14

 BIND

0.14

esar

0.14

NOT

0.13

Activations Density 0.062%

references to documentation and related files

No Comments

No Known Activations