INDEX

Explanations

expressions related to states of being or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ellung

-0.16

Äĩi

-0.16

.scalablytyped

-0.15

ãĥ³ãĥĸ

-0.15

arsing

-0.15

itar

-0.15

orra

-0.15

umhur

-0.15

 selber

-0.14

TOT

-0.14

POSITIVE LOGITS

KC

0.17

Ahead

0.16

ause

0.15

linger

0.15

 prior

0.15

Gig

0.15

 afraid

0.15

ãĥ¼ãĥķ

0.15

ola

0.15

 Bras

0.14

Activations Density 0.070%

expressions related to states of being or existence

No Comments

No Known Activations