INDEX

Explanations

mentions of awards and accolades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 vÃ´

-0.14

adiens

-0.13

Ð¾ÐºÑĥ

-0.13

 discrepan

-0.13

versed

-0.13

ialized

-0.13

 incr

-0.13

ãĤ¥

-0.13

VISIBLE

-0.13

Ske

-0.12

POSITIVE LOGITS

0.25

0.21

0.18

0.17

0.16

Activations Density 0.142%

mentions of awards and accolades

No Comments

No Known Activations