INDEX

Explanations

instances of critical or technical details within a context

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

ugins

-0.17

makta

-0.15

ETO

-0.14

empo

-0.14

_SUITE

-0.14

 Dennis

-0.14

ÑĤÑı

-0.14

æĹıèĩªæ²»

-0.14

POSITIVE LOGITS

ana

0.17

 chance

0.16

Mo

0.15

gre

0.15

 Chance

0.15

 Library

0.15

 Lock

0.14

ÑĢÐ¾Ð¼

0.14

 Carter

0.14

DeviceInfo

0.14

Activations Density 0.022%

instances of critical or technical details within a context

No Comments

No Known Activations