INDEX

Explanations

titles of articles or works, particularly in relation to specific subjects or themes

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

argo

-0.15

_INLINE

-0.15

.inf

-0.14

arlo

-0.14

inv

-0.14

anking

-0.14

 Banking

-0.14

venir

-0.14

deaux

-0.14

isa

-0.13

POSITIVE LOGITS

plusplus

0.17

INGER

0.16

ï¼Įé»ĺè®¤

0.15

inger

0.14

ìĬ¤ì½Ķ

0.14

spb

0.14

KN

0.13

 ëħ¹

0.13

Ħĸ

0.13

TINGS

0.13

Activations Density 0.070%

titles of articles or works, particularly in relation to specific subjects or themes

No Comments

No Known Activations