INDEX

Explanations

references to government and authority entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ruba

-0.17

LEM

-0.16

Ø¶Ø±

-0.15

aeda

-0.14

riter

-0.14

obo

-0.13

ãĥ³ãĥĳ

-0.13

.onOptionsItemSelected

-0.13

MeasureSpec

-0.13

WARE

-0.13

POSITIVE LOGITS

0.14

 Communities

0.14

 Knox

0.14

izi

0.13

clipse

0.13

/cc

0.13

truncate

0.13

Seb

0.13

Activations Density 0.111%

references to government and authority entities

No Comments

No Known Activations