INDEX

Explanations

terms related to insurance coverage and property protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ø§ÙħØ©

-0.17

sic

-0.17

 deal

-0.16

ninger

-0.16

ran

-0.16

enci

-0.15

 Witness

-0.15

gni

-0.15

itr

-0.14

amon

-0.14

POSITIVE LOGITS

 Loss

0.22

Policy

0.21

 loss

0.21

 Policy

0.21

 losses

0.20

-loss

0.20

 policy

0.20

Loss

0.20

 Covered

0.19

-policy

0.19

Activations Density 0.038%

terms related to insurance coverage and property protection

No Comments

No Known Activations