INDEX

Explanations

mathematical expressions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ahr

-0.19

onas

-0.17

oom

-0.17

aine

-0.15

oreach

-0.15

dorf

-0.14

MSN

-0.14

aign

-0.14

alah

-0.14

aley

-0.14

POSITIVE LOGITS

PLL

0.15

uits

0.15

rang

0.14

obus

0.14

ÙĴØ³

0.14

trs

0.14

ivol

0.14

èĮĥ

0.13

ritel

0.13

arro

0.13

Activations Density 0.056%

mathematical expressions and relationships

No Comments

No Known Activations