INDEX

Explanations

numerical data and identifiers often associated with research or academic citations

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

legate

-0.18

mÃ©na

-0.16

oppins

-0.16

uggle

-0.15

heimer

-0.14

othermal

-0.14

tright

-0.13

.opt

-0.13

lotte

-0.13

_CLIP

-0.13

POSITIVE LOGITS

ave

0.21

nda

0.17

bars

0.14

sher

0.14

 Kaiser

0.14

ItemAt

0.14

arty

0.14

ohen

0.14

 fiat

0.14

 Merrill

0.13

Activations Density 0.025%

numerical data and identifiers often associated with research or academic citations

No Comments

No Known Activations