INDEX

Explanations

terms related to regulatory frameworks and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ughty

-0.15

ARRANT

-0.15

fÃ¼

-0.15

scopic

-0.15

able

-0.14

izzare

-0.14

acious

-0.14

ify

-0.14

haf

-0.14

ittle

-0.14

POSITIVE LOGITS

atics

0.20

Ä©a

0.18

ioxide

0.17

raries

0.16

ities

0.15

agnostics

0.15

rors

0.15

erties

0.15

omencl

0.15

ulaire

0.14

Activations Density 0.561%

terms related to regulatory frameworks and policies

No Comments

No Known Activations