INDEX

Explanations

formal governmental or legal terms and actions

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

-0.16

Î³Î¬

-0.15

aid

-0.15

eko

-0.15

cri

-0.14

-urlencoded

-0.14

yen

-0.14

aida

-0.14

ëłµ

-0.14

 issuance

-0.14

POSITIVE LOGITS

 saying

0.23

pur

0.19

 guarantee

0.18

 promising

0.17

pdf

0.17

 stating

0.16

 demanding

0.16

 compelling

0.16

spec

0.15

inkel

0.15

Activations Density 0.200%

formal governmental or legal terms and actions

No Comments

No Known Activations

formal governmental or legal terms and actions

No Comments

No Known Activations