INDEX

Explanations

HTML elements and navigation-related structures in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

mere

-0.15

ocities

-0.15

chte

-0.15

mÃ®

-0.15

kud

-0.14

aucoup

-0.14

ORMAL

-0.14

Ð²Ð°Ð´

-0.14

umph

-0.14

å¼ķãģį

-0.14

POSITIVE LOGITS

 version

0.15

 side

0.15

ni

0.14

 togg

0.14

kn

0.14

ÎºÎ¹

0.13

 Project

0.13

ym

0.13

re

0.13

Activations Density 0.007%

HTML elements and navigation-related structures in the text

No Comments

No Known Activations