INDEX

Explanations

detailed descriptions and features related to visual elements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

xbe

-0.16

illance

-0.15

odzi

-0.15

.TO

-0.14

impse

-0.14

ignite

-0.14

loquent

-0.14

iqueta

-0.14

urma

-0.14

jong

-0.14

POSITIVE LOGITS

jud

0.17

 talents

0.16

ĶåĽŀ

0.16

 Äĳá»ĥ

0.16

Jud

0.15

aux

0.15

ando

0.14

instead

0.14

 Meyer

0.14

Activations Density 0.336%

detailed descriptions and features related to visual elements in various contexts

No Comments

No Known Activations