INDEX

Explanations

names of media organizations or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

lest

-0.14

que

-0.14

ctic

-0.13

Ø¨Ø§

-0.13

aic

-0.13

AFE

-0.13

SION

-0.13

 Wikip

-0.13

POSITIVE LOGITS

 exclusively

0.21

 shortly

0.17

 contributor

0.17

 ahead

0.17

 reporter

0.17

 sister

0.16

 outlet

0.16

why

0.15

 correspondent

0.15

 onDelete

0.15

Activations Density 0.027%

names of media organizations or publications

No Comments

No Known Activations