INDEX

Explanations

references to storage spaces and closets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ð½ÑĮ

-0.16

á»ĳ

-0.15

ICA

-0.15

egral

-0.15

terior

-0.14

iven

-0.14

flash

-0.14

anten

-0.14

tube

-0.13

POSITIVE LOGITS

bles

0.16

à¸±à¸ĩà¸ª

0.14

istol

0.14

ctic

0.14

orgia

0.14

(Void

0.14

opher

0.14

bour

0.13

Zuk

0.13

ãĤ¤ãĥī

0.13

Activations Density 0.018%

references to storage spaces and closets

No Comments

No Known Activations