INDEX

Explanations

terms related to employment history and resumes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÑĮÐ²

-0.18

ifs

-0.15

æ··

-0.15

 Dear

-0.15

äº¤

-0.14

panic

-0.14

æ¦ľ

-0.13

kg

-0.13

KG

-0.13

POSITIVE LOGITS

ãĤĦãĤĭ

0.16

uco

0.15

alte

0.15

 Liter

0.15

unma

0.14

ovi

0.14

HEL

0.14

ncy

0.14

æ¤

0.14

 indeed

0.13

Activations Density 0.173%

terms related to employment history and resumes

No Comments

No Known Activations