INDEX

Explanations

the word "among."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

vik

-0.16

urb

-0.15

owl

-0.15

DeltaTime

-0.15

çĶ

-0.15

itz

-0.14

.appspot

-0.14

gn

-0.14

ieber

-0.14

sel

-0.14

POSITIVE LOGITS

Å¡t

0.15

_pas

0.15

erset

0.14

AGMA

0.13

assen

0.13

Ĥ¨

0.13

gst

0.13

rij

0.13

gor

0.13

chor

0.13

Activations Density 0.022%

the word "among."

No Comments

No Known Activations