INDEX

Explanations

mentions of "engine" related terms or concepts

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

 ØªØ¨

-0.17

endum

-0.17

ATUS

-0.15

ango

-0.14

arbon

-0.14

atus

-0.14

gan

-0.13

ogy

-0.13

imitives

-0.13

BF

-0.13

POSITIVE LOGITS

assin

0.15

iren

0.14

uel

0.14

uais

0.14

æ²ī

0.14

uell

0.14

oppable

0.14

_PAD

0.14

 priorities

0.14

AYS

0.13

Activations Density 0.004%

mentions of "engine" related terms or concepts

No Comments

No Known Activations