INDEX

Explanations

HTML comment markers and navigation section headers in the document

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

brane

-0.17

alez

-0.16

åħĥ

-0.14

agues

-0.13

 Demp

-0.13

obra

-0.13

#=

-0.13

aroo

-0.13

çĥĪ

-0.13

ifest

-0.13

POSITIVE LOGITS

TEM

0.16

asiswa

0.15

divid

0.14

iad

0.14

rema

0.14

 Boyd

0.13

Coin

0.13

inks

0.13

Activations Density 0.013%

HTML comment markers and navigation section headers in the document

No Comments

No Known Activations