INDEX

Explanations

phrases indicating availability and formats of content or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

swick

-0.15

argar

-0.15

aver

-0.15

pike

-0.14

Bij

-0.14

ãĤ·ãĤ¢

-0.14

lej

-0.14

Ì§

-0.14

 Shame

-0.13

ÑĢÐ°Ð²Ð¸Ð»ÑĮ

-0.13

POSITIVE LOGITS

 Saul

0.15

íĬ

0.15

à¸´à¹Ģà¸¨à¸©

0.15

çĽĸ

0.14

Ð»ÐµÐ¼

0.14

 sÃłng

0.13

azer

0.13

èĮ¨

0.13

Activations Density 0.041%

phrases indicating availability and formats of content or products

No Comments

No Known Activations