INDEX

Explanations

symbols and expressions associated with mathematical or logical operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

JOR

-0.16

 frei

-0.16

zed

-0.16

ENSOR

-0.15

ivol

-0.15

ed

-0.15

uce

-0.14

inker

-0.14

ensor

-0.14

alom

-0.14

POSITIVE LOGITS

rud

0.16

Cop

0.16

å¾ģ

0.15

agedList

0.15

/cop

0.15

itra

0.15

agnost

0.14

pga

0.14

illin

0.14

ModelError

0.14

Activations Density 0.000%

symbols and expressions associated with mathematical or logical operations

No Comments

No Known Activations