INDEX

Explanations

mentions of Belgium or Belgian-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

adge

-0.21

inand

-0.16

illac

-0.15

beam

-0.14

ooks

-0.14

å´ĩ

-0.14

dden

-0.13

lc

-0.13

ª

-0.13

etal

-0.13

POSITIVE LOGITS

icit

0.18

xad

0.17

SEMB

0.15

Ø³ÙĪØ¨

0.15

_traits

0.15

Dam

0.14

ï¿¥

0.14

á»ĭch

0.14

Ð¾Ð»Ð¾Ð¼

0.14

Activations Density 0.004%

mentions of Belgium or Belgian-related terms

No Comments

No Known Activations

mentions of Belgium or Belgian-related terms

No Comments

No Known Activations