INDEX

Explanations

symbols and structural elements in text, indicating a strong focus on organization and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

IMIT

-0.17

Abr

-0.16

vÃŃ

-0.15

andon

-0.14

ÏĪÎ·

-0.14

ckett

-0.14

.idea

-0.14

ÑıÑĤÐµÐ»ÑĮ

-0.14

wit

-0.14

vore

-0.14

POSITIVE LOGITS

 Reich

0.16

.cgi

0.16

udio

0.15

 ÑģÐ¾Ð¿

0.14

REA

0.14

substr

0.14

 Kami

0.14

 consent

0.14

Activations Density 0.004%

symbols and structural elements in text, indicating a strong focus on organization and formatting

No Comments

No Known Activations