INDEX

Explanations

phrases related to decision-making or conclusions reached after deliberation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

jak

-0.15

Ã©es

-0.15

Å¥

-0.15

è¾°

-0.14

 unregister

-0.14

ãĤ¹ãĥĨãĤ£

-0.14

Ø±ÙĪØ¯

-0.13

_printer

-0.13

 Graham

-0.13

Ð±Ð°Ñĩ

-0.13

POSITIVE LOGITS

 eventually

0.18

 finally

0.17

 eventual

0.17

bul

0.15

ãĥ¼ãĤ¸

0.15

timeofday

0.15

OUGH

0.15

finally

0.15

cker

0.14

 Eventually

0.14

Activations Density 0.178%

phrases related to decision-making or conclusions reached after deliberation

No Comments

No Known Activations