INDEX

Explanations

references to investors and investment-related terms

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

eno

-0.18

ene

-0.17

-0.16

enko

-0.15

 Kiss

-0.15

 slut

-0.14

 Slut

-0.14

 Disclosure

-0.14

ree

-0.14

itra

-0.13

POSITIVE LOGITS

quip

0.17

quette

0.16

plr

0.15

Å¡il

0.15

haps

0.15

MBER

0.14

 Relations

0.14

ãģĵãĤĵãģ«

0.14

ronym

0.14

lsi

0.14

Activations Density 0.007%

references to investors and investment-related terms

No Comments

No Known Activations