INDEX

Explanations

references to titles or designations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

steen

-0.18

ett

-0.16

viz

-0.15

/tiny

-0.14

av

-0.14

prit

-0.14

stakes

-0.14

enis

-0.14

lek

-0.14

PK

-0.14

POSITIVE LOGITS

ushima

0.16

istros

0.15

åĢĻ

0.14

cosystem

0.14

gend

0.14

andest

0.14

 Bout

0.14

lename

0.14

EventListener

0.14

aptops

0.14

Activations Density 0.026%

references to titles or designations

No Comments

No Known Activations