INDEX

Explanations

phrases related to maximizing benefits or outcomes

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

éŁ¿

-0.16

sworth

-0.15

ile

-0.14

Ease

-0.14

 forb

-0.14

ilename

-0.14

isset

-0.13

ÙħØ§

-0.13

_pb

-0.13

POSITIVE LOGITS

lap

0.20

usch

0.17

clerosis

0.15

QN

0.15

lst

0.15

oby

0.15

mise

0.14

chein

0.14

ardi

0.14

ofi

0.14

Activations Density 0.029%

phrases related to maximizing benefits or outcomes

No Comments

No Known Activations