INDEX

Explanations

variations of the word "alt" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÏĥÎ¿Î½

-0.15

hardt

-0.14

psilon

-0.14

ytt

-0.14

 electr

-0.14

bellion

-0.14

ÎµÎ¹Î±

-0.14

holds

-0.13

fono

-0.13

formance

-0.13

POSITIVE LOGITS

idor

0.15

INGER

0.15

olian

0.15

iers

0.15

shal

0.14

 Victoria

0.14

arget

0.14

ucc

0.14

urous

0.14

Activations Density 0.004%

variations of the word "alt" and its derivatives

No Comments

No Known Activations