INDEX

Explanations

words that indicate conditions, expectations, and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Vu

-0.16

haft

-0.15

eced

-0.15

erece

-0.15

lef

-0.14

ared

-0.14

();)

-0.14

lif

-0.14

arias

-0.14

POSITIVE LOGITS

æ¨Ĥ

0.18

ãģıãĤī

0.16

idor

0.15

ino

0.14

atin

0.13

chair

0.13

ÑıÐ¼

0.13

engeance

0.13

 gang

0.13

odash

0.13

Activations Density 0.001%

words that indicate conditions, expectations, and qualifications

No Comments

No Known Activations