INDEX

Explanations

references to queues and lines of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quist

-0.16

Elk

-0.16

inger

-0.16

éİ

-0.16

 Match

-0.15

umen

-0.15

 doubles

-0.15

match

-0.15

INGER

-0.14

iotics

-0.14

POSITIVE LOGITS

ange

0.15

eba

0.15

à¹Īà¸§à¸ĩ

0.15

argent

0.15

 Cloth

0.14

imes

0.14

__':↵

0.14

.CG

0.13

emble

0.13

anity

0.13

Activations Density 0.039%

references to queues and lines of people

No Comments

No Known Activations