INDEX

Explanations

elements related to logos and branding

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

 numbered

-0.18

 marked

-0.16

marked

-0.15

Ð¾Ð»Ð¾Ñģ

-0.15

 markings

-0.15

 marks

-0.14

 Hind

-0.14

 Marks

-0.13

ultip

-0.13

POSITIVE LOGITS

 surrounded

0.17

 center

0.17

 repeated

0.17

Against

0.16

 against

0.16

against

0.16

 below

0.16

 handset

0.15

.center

0.15

Activations Density 0.063%

elements related to logos and branding

No Comments

No Known Activations