INDEX

Explanations

references to "material" in various contexts related to discussion or analysis

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

eg

-0.19

esModule

-0.17

es

-0.17

ess

-0.16

amilia

-0.16

ed

-0.16

kara

-0.16

ORS

-0.15

nar

-0.15

 trÃ¬

-0.15

POSITIVE LOGITS

istic

0.26

ity

0.24

ized

0.22

ize

0.22

izing

0.22

UnderTest

0.21

è´¨

0.20

è³ª

0.20

ization

0.20

ien

0.19

Activations Density 0.029%

references to "material" in various contexts related to discussion or analysis

No Comments

No Known Activations