INDEX

Explanations

questions and phrases indicating conditions or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

vi

-0.16

activex

-0.15

ago

-0.15

ickle

-0.15

apolis

-0.15

hide

-0.14

æĹĹ

-0.14

.bn

-0.13

DX

-0.13

DX

-0.13

POSITIVE LOGITS

 Welfare

0.16

iniz

0.16

COMPARE

0.15

ecess

0.14

nex

0.14

 Interest

0.14

weeted

0.14

matcher

0.14

lub

0.14

(Have

0.14

Activations Density 0.002%

questions and phrases indicating conditions or requirements

No Comments

No Known Activations