INDEX

Explanations

questions and phrases related to methods or procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ãĥ«ãĥī

-0.17

xing

-0.17

egas

-0.16

mlin

-0.16

borg

-0.16

_DECLARE

-0.16

.sponge

-0.15

ÑĢÐ¸Ñĩ

-0.15

oje

-0.15

å¹¹

-0.15

POSITIVE LOGITS

½

0.15

soever

0.15

 Wass

0.15

illum

0.14

omb

0.14

 appreciation

0.13

owitz

0.13

/how

0.13

ess

0.13

Activations Density 0.052%

questions and phrases related to methods or procedures

No Comments

No Known Activations