INDEX

Explanations

references to obstacles and barriers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ilo

-0.15

ÛĮÚ©ÛĮ

-0.14

_EXTENSIONS

-0.14

à¥Ģà¤¤à¤°

-0.14

èµ·æĿ¥

-0.14

ESC

-0.14

venes

-0.13

chy

-0.13

ERICA

-0.13

orman

-0.13

POSITIVE LOGITS

orts

0.19

0.17

/bar

0.15

bars

0.15

/conf

0.15

ìĤ¬íķŃ

0.15

DEX

0.15

/block

0.15

Activations Density 0.029%

references to obstacles and barriers in various contexts

No Comments

No Known Activations