INDEX

Explanations

references to employment and job-related experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

itia

-0.16

à¤Ĥà¤Ń

-0.14

Ð¸Ð»Ð°

-0.14

Wid

-0.14

-0.13

izer

-0.13

tl

-0.13

á»¥

-0.13

 Conway

-0.13

idges

-0.13

POSITIVE LOGITS

 jobs

0.56

job

0.54

 Jobs

0.48

job

0.47

JOB

0.44

 employment

0.43

jobs

0.43

Job

0.43

Job

0.43

-job

0.42

Activations Density 0.155%

references to employment and job-related experiences

No Comments

No Known Activations