INDEX

Explanations

nouns and determiners associated with hierarchical structures or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Ð¼ÐµÑĩ

-0.15

Ð²Ð¾Ð»Ñı

-0.14

èĤĮ

-0.13

bak

-0.13

oftware

-0.13

ria

-0.13

rij

-0.13

adu

-0.12

metics

-0.12

ills

-0.12

POSITIVE LOGITS

 same

0.26

same

0.21

 misma

0.20

 mismo

0.19

ses

0.15

 mesma

0.15

jen

0.15

 majority

0.15

 mÃªme

0.15

 siguiente

0.14

Activations Density 0.082%

nouns and determiners associated with hierarchical structures or classifications

No Comments

No Known Activations

nouns and determiners associated with hierarchical structures or classifications

No Comments

No Known Activations