INDEX

Explanations

terms related to unemployment and job loss

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Î¼Î¼Î±

-0.18

roje

-0.15

 Ð¿Ð°ÑĢÐ°

-0.14

jee

-0.14

 Canc

-0.14

nett

-0.14

ila

-0.14

.hw

-0.13

 McCartney

-0.13

 conserv

-0.13

POSITIVE LOGITS

eteria

0.15

uxe

0.15

 sincer

0.15

0.14

ognito

0.14

weeney

0.14

odel

0.14

cripts

0.13

urf

0.13

gap

0.13

Activations Density 0.006%

terms related to unemployment and job loss

No Comments

No Known Activations