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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Bilg

-0.18

Î¼Î¼Î±

-0.16

VID

-0.16

abo

-0.15

Ð»Ð¾Ð²Ð°

-0.15

UPC

-0.14

ãģļ

-0.14

 Ð¼Ð°Ð»ÑĮ

-0.14

 Interr

-0.14

POSITIVE LOGITS

wiÄħ

0.14

uron

0.14

ors

0.14

Fay

0.14

Unused

0.14

implicit

0.13

cano

0.13

cj

0.13

hawk

0.13

aks

0.13

Activations Density 0.008%

terms related to unemployment and job loss

No Comments

No Known Activations