INDEX

Explanations

expressions of anticipation and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

cheid

-0.16

lick

-0.15

ubern

-0.15

ibbon

-0.15

inis

-0.15

alez

-0.14

entials

-0.14

GENCY

-0.13

-Cs

-0.13

imits

-0.13

POSITIVE LOGITS

indow

0.16

zano

0.16

MES

0.16

 your

0.15

MES

0.14

_prompt

0.14

æ´¥

0.14

[d

0.14

_NC

0.13

elerle

0.13

Activations Density 0.071%

expressions of anticipation and appreciation

No Comments

No Known Activations