INDEX

Explanations

phrases related to movement and positioning in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ERRU

-0.16

oten

-0.14

aille

-0.14

Ø·Ùģ

-0.14

otros

-0.13

ulos

-0.13

urette

-0.13

æĹıèĩªæ²»

-0.13

uzzi

-0.13

 ìĭ¸

-0.13

POSITIVE LOGITS

lb

0.24

leg

0.24

LB

0.24

 slog

0.22

ump

0.21

 misc

0.20

 york

0.20

 square

0.20

 cover

0.20

 edge

0.20

Activations Density 0.011%

phrases related to movement and positioning in a context

No Comments

No Known Activations