INDEX

Explanations

descriptions and actions related to exploration and travel through various landscapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.18

ureau

-0.17

DBC

-0.16

\Schema

-0.16

emer

-0.16

erah

-0.15

ÃŃte

-0.14

ubl

-0.14

_RCC

-0.14

POSITIVE LOGITS

 countryside

0.16

atto

0.15

 familiar

0.15

 unfamiliar

0.15

 shortcut

0.15

 unknown

0.15

 forests

0.14

 Moran

0.14

ardo

0.14

abe

0.14

Activations Density 0.095%

descriptions and actions related to exploration and travel through various landscapes

No Comments

No Known Activations