INDEX

Explanations

mentions of ingredients 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

jid

-0.16

ãģ¾ãģŁ

-0.16

Ã¶tt

-0.15

ARP

-0.15

thy

-0.15

 cref

-0.14

ej

-0.14

ff

-0.14

aron

-0.14

rak

-0.14

POSITIVE LOGITS

chaft

0.19

prene

0.18

æĿĲ

0.18

EDA

0.18

webs

0.17

Ð¾Ð²ÐµÑĢ

0.16

oftware

0.15

 ingredients

0.15

ÐµÐ»ÐµÑĦÐ¾Ð½

0.15

Activations Density 0.015%

mentions of ingredients in various contexts

No Comments

No Known Activations