INDEX

Explanations

references to specific numeric values or data related to size, quantities, 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

eten

-0.16

Äįit

-0.15

orno

-0.15

Binary

-0.14

rag

-0.14

ÐĶÐĲ

-0.14

/ros

-0.14

aison

-0.14

ufen

-0.14

akis

-0.14

POSITIVE LOGITS

 Temple

0.18

allis

0.17

 Cent

0.17

 Inline

0.16

 temple

0.15

 folding

0.15

 Folding

0.15

 Temp

0.15

.inline

0.15

hor

0.15

Activations Density 0.035%

references to specific numeric values or data related to size, quantities, or classifications

No Comments

No Known Activations