INDEX

Explanations

occurrences of the abbreviation "i.e." which is typically used to clarify or provide examples

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

pf

-0.15

.gg

-0.15

pageIndex

-0.15

 McKay

-0.14

adolu

-0.14

Ø§Øµ

-0.14

erson

-0.14

viÄį

-0.14

ica

-0.14

RCT

-0.14

POSITIVE LOGITS

uzey

0.16

ripp

0.15

âĦĸâĦĸ

0.15

izio

0.15

spir

0.14

oppins

0.14

udas

0.14

jeta

0.14

0.13

uetype

0.13

Activations Density 0.013%

occurrences of the abbreviation "i.e." which is typically used to clarify or provide examples

No Comments

No Known Activations