INDEX

Explanations

references to significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ÎµÎ¯ÏĤ

-0.14

tÃŃ

-0.14

IVEN

-0.14

antt

-0.14

enus

-0.13

oric

-0.13

±Ð¾ÑĤ

-0.13

istring

-0.13

ziej

-0.13

vailability

-0.13

POSITIVE LOGITS

ä»½

0.20

ato

0.17

>\<^

0.15

oyer

0.14

 porr

0.14

 ninh

0.14

é¦Ļ

0.14

odos

0.13

Ń

0.13

Activations Density 0.036%

references to significant events or milestones

No Comments

No Known Activations