INDEX

Explanations

connectors and pronouns that indicate relationships or actions within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 DISCLAIM

-0.17

utenberg

-0.15

Ú©ÛĮÙĦ

-0.15

$MESS

-0.15

rafted

-0.15

Î½Î¬

-0.15

thur

-0.14

ÐºÑĤÐ°

-0.14

 COMMENTS

-0.14

ucz

-0.14

POSITIVE LOGITS

ativ

0.15

 victims

0.15

 replay

0.14

bar

0.14

 Woodward

0.14

 confidence

0.14

 confident

0.14

 tech

0.14

Activations Density 0.001%

connectors and pronouns that indicate relationships or actions within a narrative

No Comments

No Known Activations