INDEX

Explanations

the word "which" indicating its focus on relative clauses or specific clarifications in sentences

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

jour

-0.15

xu

-0.14

UEL

-0.14

iquer

-0.14

ja

-0.14

rive

-0.14

 Hath

-0.14

oose

-0.14

à¹ĥà¸Ī

-0.13

ä¾

-0.13

POSITIVE LOGITS

roker

0.16

soever

0.15

undler

0.14

éłĨ

0.14

anity

0.14

á»¥

0.13

EMA

0.13

 Sentry

0.13

odate

0.13

/by

0.13

Activations Density 0.023%

the word "which" indicating its focus on relative clauses or specific clarifications in sentences

No Comments

No Known Activations