INDEX

Explanations

punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.ibm

-0.15

vir

-0.15

NI

-0.15

è¸

-0.14

amac

-0.14

erland

-0.14

enties

-0.14

ilt

-0.14

edges

-0.13

.Ap

-0.13

POSITIVE LOGITS

 http

0.20

nam

0.20

 https

0.19

xyz

0.17

xt

0.17

 EVAL

0.15

amber

0.15

zan

0.15

luz

0.15

vel

0.14

Activations Density 0.000%

punctuation marks

No Comments

No Known Activations