INDEX

Explanations

references to sections and appendices in documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gn

-0.17

ston

-0.16

eldon

-0.15

miss

-0.14

chez

-0.14

MISS

-0.14

 miss

-0.14

 reflex

-0.14

åºľ

-0.13

pt

-0.13

POSITIVE LOGITS

ayi

0.17

pire

0.15

Ã¢l

0.15

/Core

0.15

krom

0.15

arend

0.14

ornings

0.14

acob

0.14

iyi

0.14

RequestMethod

0.14

Activations Density 0.022%

references to sections and appendices in documents

No Comments

No Known Activations