INDEX

Explanations

names of notable individuals and authors related to the content discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

/WebAPI

-0.15

ÐµÑĢÐ¶

-0.15

 DISPATCH

-0.15

stanbul

-0.15

aeda

-0.15

SupportedContent

-0.14

sgi

-0.14

Ø¨Ø§Ø²

-0.14

 ÎĶÎµ

-0.14

.ak

-0.14

POSITIVE LOGITS

 criminal

0.16

 Vent

0.15

ann

0.15

bit

0.15

 past

0.14

ito

0.14

 lower

0.14

id

0.13

Activations Density 0.039%

names of notable individuals and authors related to the content discussed

No Comments

No Known Activations