INDEX

Explanations

references to levels or stages in a hierarchy or system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

assin

-0.15

åĴ

-0.14

alles

-0.14

 Russell

-0.14

amarin

-0.14

Chr

-0.14

Ã¡na

-0.14

eden

-0.14

 done

-0.14

oom

-0.14

POSITIVE LOGITS

 Means

0.15

orst

0.15

Means

0.14

_ARCHIVE

0.14

ISTS

0.14

ajor

0.14

ists

0.14

¼åĲĪ

0.13

ĺè®¤

0.13

-lfs

0.13

Activations Density 0.162%

references to levels or stages in a hierarchy or system

No Comments

No Known Activations