INDEX

Explanations

numerical values and percentages related to statistics and data in various contexts

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

-0.17

-0.16

å±

-0.16

-0.15

io

-0.15

 clearfix

-0.14

 bush

-0.14

POSITIVE LOGITS

ouro

0.17

(æľĪ

0.16

umlu

0.16

postalcode

0.15

egra

0.15

/Dk

0.15

(æĹ¥

0.15

uchos

0.15

.EventType

0.15

/Gate

0.14

Activations Density 0.054%

numerical values and percentages related to statistics and data in various contexts

No Comments

No Known Activations