INDEX

Explanations

terms related to growth and enhancement in various contexts

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

loff

-0.15

utton

-0.15

UTTON

-0.15

 responsiveness

-0.15

iÄį

-0.14

_ONCE

-0.14

ello

-0.14

_PRIORITY

-0.14

ricing

-0.14

å½¹

-0.14

POSITIVE LOGITS

 confidence

0.19

apas

0.18

aware

0.18

 awareness

0.18

 Awareness

0.17

agna

0.17

 chances

0.16

abd

0.15

 colabor

0.15

 understanding

0.15

Activations Density 0.123%

terms related to growth and enhancement in various contexts

No Comments

No Known Activations