INDEX

Explanations

terms related to job roles, responsibilities, and work-related expenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ãĥŃãĥ¼

-0.17

angan

-0.17

latlong

-0.17

plain

-0.16

hti

-0.16

Ð¾Ð»Ñı

-0.16

ternet

-0.15

ounter

-0.15

ATAB

-0.15

iston

-0.15

POSITIVE LOGITS

sto

0.18

(s

0.16

åĲĽ

0.15

0.14

asso

0.14

arsers

0.14

 algun

0.14

quia

0.14

rels

0.14

[s

0.14

Activations Density 1.372%

terms related to job roles, responsibilities, and work-related expenses

No Comments

No Known Activations