INDEX

Explanations

significant terms or phrases indicating conditions or criteria that require careful consideration or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iaux

-0.19

andle

-0.18

vik

-0.17

ANDLE

-0.15

yre

-0.15

.Abs

-0.15

orre

-0.15

ayet

-0.14

holm

-0.14

ssp

-0.14

POSITIVE LOGITS

den

0.14

 warm

0.14

 staples

0.14

Pen

0.14

 mass

0.14

udiant

0.14

tro

0.14

atre

0.13

Pen

0.13

adora

0.13

Activations Density 0.001%

significant terms or phrases indicating conditions or criteria that require careful consideration or evaluation

No Comments

No Known Activations