INDEX

Explanations

references to specific visual elements or descriptions in a narrative

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

ooky

-0.18

inery

-0.16

Mods

-0.15

.onView

-0.15

tabpanel

-0.15

ëŀĳ

-0.14

bek

-0.14

minent

-0.14

-fontawesome

-0.14

modifiable

-0.14

POSITIVE LOGITS

 Hack

0.16

Hack

0.15

%č↵

0.15

hack

0.14

 equip

0.14

ãĥ©ãĥĥãĤ¯

0.14

 circum

0.14

 KÃ¼r

0.14

è½

0.14

auc

0.14

Activations Density 0.093%

references to specific visual elements or descriptions in a narrative

No Comments

No Known Activations