INDEX

Explanations

references to individuals' job titles, career actions, and organizational roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iken

-0.17

ius

-0.16

iks

-0.15

ased

-0.14

porter

-0.14

otle

-0.14

opp

-0.14

?q

-0.14

azio

-0.14

elta

-0.14

POSITIVE LOGITS

è¯¥

0.36

è©²

0.29

 this

0.20

ï¼Įè¯¥

0.20

è¿Ļä¸ª

0.19

 ÑįÑĤÐ¾ÑĤ

0.19

 íķ´ëĭ¹

0.18

this

0.18

 ÑįÑĤÐ¾Ð¹

0.18

anine

0.17

Activations Density 0.554%

references to individuals' job titles, career actions, and organizational roles

No Comments

No Known Activations