INDEX

Explanations

phrases related to causes and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

anke

-0.14

âĶ´

-0.14

IGH

-0.14

jedn

-0.14

vier

-0.14

 Bent

-0.13

ìĪł

-0.13

maal

-0.13

Dah

-0.13

tagName

-0.13

POSITIVE LOGITS

onium

0.15

krom

0.15

utton

0.15

riel

0.14

essions

0.14

ëħĢ

0.14

adio

0.14

uche

0.14

geom

0.14

iversit

0.14

Activations Density 0.068%

phrases related to causes and consequences

No Comments

No Known Activations