INDEX

Explanations

numerical values related to dates and significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rupa

-0.17

kud

-0.16

meer

-0.16

nud

-0.16

byn

-0.15

elden

-0.15

afort

-0.14

rub

-0.14

 Mach

-0.14

oice

-0.14

POSITIVE LOGITS

ç¸

0.16

 Chambers

0.15

 semiclass

0.15

cols

0.15

ad

0.15

[$_

0.14

 âĹĦ

0.14

bek

0.14

/null

0.14

Ext

0.13

Activations Density 0.075%

numerical values related to dates and significant events

No Comments

No Known Activations