INDEX

Explanations

high-frequency words that indicate relationships or connections

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

ific

-0.17

Ob

-0.15

.u

-0.15

 horn

-0.14

obus

-0.14

 Mess

-0.13

 Contrib

-0.13

 Ø±Ø§Ø³Øª

-0.13

_generic

-0.13

IS

-0.13

POSITIVE LOGITS

_userdata

0.16

ãĥªãĤ«

0.15

ijkstra

0.15

æ²¢

0.14

ÏĮÏģ

0.14

 TORT

0.14

uckle

0.14

ateway

0.14

Æ°a

0.14

prite

0.14

Activations Density 0.006%

high-frequency words that indicate relationships or connections

No Comments

No Known Activations