INDEX

Explanations

phrases or terms related to being "under" a certain threshold or condition

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

owitz

-0.14

posix

-0.14

fully

-0.14

conti

-0.14

jo

-0.14

ner

-0.14

erna

-0.13

ably

-0.13

rox

-0.13

POSITIVE LOGITS

neath

0.20

 wing

0.16

eltas

0.16

sea

0.15

whelming

0.15

 pretext

0.15

 wings

0.15

ERG

0.14

ubat

0.14

nop

0.14

Activations Density 0.044%

phrases or terms related to being "under" a certain threshold or condition

No Comments

No Known Activations