INDEX

Explanations

geographic locations and addresses

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

eldorf

-0.17

ith

-0.15

inha

-0.14

feld

-0.14

inho

-0.13

ects

-0.13

 Saud

-0.13

/version

-0.13

acha

-0.13

Gut

-0.13

POSITIVE LOGITS

raphics

0.16

ysis

0.15

0.14

 consenting

0.14

ãĥ¯ãĥ¼

0.14

ulis

0.14

_principal

0.14

imizer

0.13

áº¡ng

0.13

åŃĿ

0.13

Activations Density 0.165%

geographic locations and addresses

No Known Activations