INDEX

Explanations

references to "on-site" activities or locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ero

-0.16

çİĭ

-0.15

ray

-0.14

Ð»Ð°Ð²

-0.14

 Holmes

-0.14

amd

-0.14

 Kids

-0.13

ray

-0.13

ays

-0.13

azon

-0.13

POSITIVE LOGITS

aterno

0.17

neau

0.17

ewise

0.15

abbo

0.14

ridge

0.14

 benefiting

0.14

 optics

0.14

atab

0.14

Vig

0.14

gren

0.14

Activations Density 0.008%

references to "on-site" activities or locations

No Comments

No Known Activations