INDEX

Explanations

repeated use of the word "by."

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

ansa

-0.16

angan

-0.15

prend

-0.15

oyer

-0.15

eus

-0.14

ynamo

-0.14

peria

-0.13

avar

-0.13

.rawValue

-0.13

 seins

-0.13

POSITIVE LOGITS

0.17

ium

0.16

riere

0.15

akit

0.14

ulton

0.14

0.13

requencies

0.13

usat

0.13

ª

0.13

Activations Density 0.080%

repeated use of the word "by."

No Comments

No Known Activations