INDEX

Explanations

terms related to "disc" or "disk"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inks

-0.15

ÙĪÙĦØ©

-0.15

uty

-0.15

ioned

-0.15

itest

-0.15

Uhr

-0.15

ares

-0.15

ymes

-0.14

croft

-0.14

terior

-0.14

POSITIVE LOGITS

arding

0.22

ursive

0.20

/disc

0.20

losures

0.18

disc

0.18

-disc

0.18

ipline

0.18

iplinary

0.18

ussions

0.17

 Disc

0.17

Activations Density 0.020%

terms related to "disc" or "disk"

No Comments

No Known Activations