INDEX

Explanations

phrases related to employment and job searching challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

eba

-0.16

otos

-0.15

æĴ¤

-0.14

inally

-0.14

ÙĬØ§Øª

-0.14

izer

-0.14

ANGO

-0.14

borg

-0.13

indow

-0.13

_BUFF

-0.13

POSITIVE LOGITS

 employment

0.65

 Employment

0.54

 jobs

0.49

employment

0.48

 work

0.44

job

0.42

 Jobs

0.41

jobs

0.40

 emploi

0.38

 employ

0.38

Activations Density 0.161%

phrases related to employment and job searching challenges

No Comments

No Known Activations