INDEX

Explanations

numerical values related to age or time duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

stal

-0.17

ÐµÐ½Ñĥ

-0.15

ipop

-0.14

spb

-0.14

è¦

-0.14

grim

-0.14

fos

-0.14

 Novel

-0.13

andon

-0.13

 novel

-0.13

POSITIVE LOGITS

ari

0.16

 Respect

0.15

oling

0.15

asty

0.14

Reducer

0.14

ARI

0.14

#ac

0.14

0.13

 alike

0.13

Activations Density 0.063%

numerical values related to age or time duration

No Comments

No Known Activations