INDEX

Explanations

adjectives and phrases related to improvement or enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.nr

-0.15

 Safety

-0.15

alfa

-0.14

chied

-0.14

ecz

-0.14

çĽ´æĴŃ

-0.14

Raq

-0.14

ids

-0.14

blade

-0.14

anki

-0.14

POSITIVE LOGITS

çīĪ

0.16

asi

0.16

ë§¤

0.15

 version

0.15

sol

0.14

ATUS

0.14

recated

0.14

ouz

0.14

 flood

0.14

sol

0.13

Activations Density 0.206%

adjectives and phrases related to improvement or enhancement

No Comments

No Known Activations