INDEX

Explanations

objects and containers related to display and storage

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

 Waters

-0.14

bane

-0.14

aight

-0.14

/runtime

-0.14

 Ø§Ø°

-0.14

itus

-0.14

 Traverse

-0.14

kes

-0.14

irth

-0.14

Ñĥ

-0.14

POSITIVE LOGITS

ÑĩÐ°ÑĤ

0.17

flip

0.17

/on

0.15

 Eins

0.15

zin

0.15

issent

0.15

 Stam

0.14

èľľ

0.14

iline

0.14

orrent

0.14

Activations Density 0.107%

objects and containers related to display and storage

No Comments

No Known Activations