INDEX

Explanations

references to the Euro and related economic terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 ChÃŃ

-0.15

cest

-0.15

ãĥ©ãĤ¤ãĥĪ

-0.15

ouri

-0.15

chy

-0.15

cox

-0.14

 nÃło

-0.14

ynchronously

-0.14

dating

-0.14

è¡Ľ

-0.14

POSITIVE LOGITS

hound

0.16

anness

0.15

ŀĭ

0.14

-wide

0.14

umbs

0.14

lys

0.13

osate

0.13

sik

0.13

amente

0.13

Activations Density 0.012%

references to the Euro and related economic terms

No Comments

No Known Activations