INDEX

Explanations

instances of the preposition "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ounced

-0.19

cluding

-0.17

pline

-0.17

structors

-0.16

alon

-0.16

icio

-0.16

iced

-0.15

mÃ©na

-0.15

.scalablytyped

-0.15

POSITIVE LOGITS

ane

0.19

ANE

0.18

aus

0.18

human

0.18

bred

0.17

auth

0.16

anel

0.16

thr

0.16

ANI

0.16

abil

0.15

Activations Density 0.051%

instances of the preposition "in."

No Comments

No Known Activations

instances of the preposition "in."

No Comments

No Known Activations