INDEX

Explanations

prepositions and their contextual use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ç¹Ķ

-0.15

bai

-0.14

abela

-0.14

antiago

-0.14

ãĥĦ

-0.13

latin

-0.13

ãģĩ

-0.13

_ETH

-0.13

POSITIVE LOGITS

/from

0.15

_atual

0.15

ÙĪØ·

0.15

omat

0.15

ounder

0.15

ISTA

0.15

asty

0.14

ahoo

0.14

ined

0.14

plevel

0.14

Activations Density 0.051%

prepositions and their contextual use

No Comments

No Known Activations