INDEX

Explanations

mathematical symbols and notations related to measurements or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

gre

-0.15

ivet

-0.15

lico

-0.15

 nextPage

-0.14

ĽĪ

-0.14

umps

-0.14

vard

-0.14

Ãªu

-0.13

isclosed

-0.13

imals

-0.13

POSITIVE LOGITS

kip

0.15

tun

0.14

 Sovere

0.14

AttributeName

0.14

 condu

0.14

 Toastr

0.14

ģ

0.13

Svc

0.13

raries

0.13

Activations Density 0.010%

mathematical symbols and notations related to measurements or comparisons

No Comments

No Known Activations