INDEX

Explanations

references to notable achievements or significant placements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

uilder

-0.15

ÎºÎ±Î½

-0.12

rier

-0.12

 uprav

-0.12

UAGE

-0.12

COPE

-0.12

à¹Ģà¸īà¸¥

-0.11

à¥Įà¤¦

-0.11

à¸²à¸Ľ

-0.11

ĶåĽŀ

-0.11

POSITIVE LOGITS

 place

1.20

 places

0.94

place

0.94

 Place

0.94

-place

0.91

Place

0.87

 PLACE

0.86

_place

0.82

.place

0.80

 lugar

0.77

Activations Density 0.360%

references to notable achievements or significant placements

No Comments

No Known Activations