INDEX

Explanations

phrases related to requests and appeals for action

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

atk

-0.17

-0.15

ainless

-0.13

/by

-0.13

stu

-0.13

swire

-0.13

Ã

-0.13

ÑĢÐ¾Ð²Ð°

-0.13

zer

-0.13

pta

-0.13

POSITIVE LOGITS

 upon

0.45

 attention

0.44

dib

0.35

 into

0.34

 Attention

0.33

out

0.33

upon

0.32

ously

0.32

 forth

0.32

attention

0.31

Activations Density 0.050%

phrases related to requests and appeals for action

No Comments

No Known Activations