INDEX

Explanations

references to employment and job-related activities

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

iage

-0.17

/cs

-0.16

EMA

-0.15

SEQ

-0.15

pra

-0.15

oute

-0.14

enti

-0.14

é¢¨

-0.14

ukkan

-0.14

lendir

-0.14

POSITIVE LOGITS

 jobs

0.43

 employment

0.40

 Jobs

0.39

jobs

0.38

job

0.35

Jobs

0.33

 work

0.31

 Employment

0.31

job

0.31

employment

0.31

Activations Density 0.264%

references to employment and job-related activities

No Comments

No Known Activations