INDEX

Explanations

references to reports or statistics related to events and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Raphael

-0.17

-0.15

ks

-0.15

 ÐºÐ¾Ð½ÑĤÑĢÐ°

-0.15

/stdc

-0.15

ements

-0.14

yms

-0.14

à¤ľà¤¨

-0.14

ongo

-0.14

coni

-0.14

POSITIVE LOGITS

Nos

0.18

aire

0.16

ige

0.15

anca

0.15

uger

0.14

plural

0.14

issance

0.14

.peek

0.14

 Holmes

0.14

yte

0.14

Activations Density 0.838%

references to reports or statistics related to events and their effects

No Comments

No Known Activations