INDEX

Explanations

complex sentence structures or clauses that indicate comparisons or conditions

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

Ã¢ng

-0.16

ulu

-0.16

Wunused

-0.15

 Turns

-0.15

 Plus

-0.15

 Worldwide

-0.14

uiten

-0.14

gs

-0.14

ibase

-0.14

GS

-0.14

POSITIVE LOGITS

itis

0.18

nor

0.16

 nothing

0.15

such

0.15

 such

0.14

it

0.14

oris

0.14

Â¥

0.14

ernet

0.14

 Nothing

0.14

Activations Density 0.401%

complex sentence structures or clauses that indicate comparisons or conditions

No Comments

No Known Activations