INDEX

Explanations

indicators of job positions and employment types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

decade

-0.15

ojis

-0.15

 DÃ¼n

-0.14

 nightly

-0.14

Å¾itÃŃ

-0.14

 Trades

-0.14

ANJI

-0.13

arias

-0.13

_INTERVAL

-0.13

IDDEN

-0.13

POSITIVE LOGITS

/full

0.21

 partial

0.21

 full

0.20

 permanent

0.19

 Full

0.19

 part

0.19

 flexible

0.18

-full

0.18

 Flexible

0.18

 Voll

0.18

Activations Density 0.053%

indicators of job positions and employment types

No Comments

No Known Activations