INDEX

Explanations

references to authoritative figures or legal concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

olith

-0.15

daemon

-0.15

rella

-0.14

 pert

-0.14

xo

-0.14

ol

-0.14

eniable

-0.13

SPA

-0.13

gyr

-0.13

 \č↵

-0.13

POSITIVE LOGITS

 bell

0.15

biÃªn

0.15

bell

0.14

cid

0.14

bett

0.14

esser

0.14

 follower

0.14

yles

0.13

IFS

0.13

_THREAD

0.13

Activations Density 0.019%

references to authoritative figures or legal concepts

No Comments

No Known Activations