INDEX

Explanations

words related to strength and influence

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

uco

-0.18

.Safe

-0.16

agal

-0.15

oram

-0.15

icare

-0.15

ê

-0.15

orum

-0.15

aÄį

-0.15

ÙĩÙĨ

-0.14

ViewById

-0.14

POSITIVE LOGITS

 powerful

0.35

/power

0.30

power

0.29

 Powerful

0.28

 power

0.28

powers

0.26

 potent

0.25

 powers

0.25

-power

0.23

 Power

0.23

Activations Density 0.086%

words related to strength and influence

No Comments

No Known Activations