INDEX

Explanations

dialogue and conversational structures within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

å¾½

-0.17

Conditions

-0.15

ehler

-0.14

erken

-0.14

aktu

-0.14

à¹Ģà¸Ī

-0.14

éĢļ

-0.14

ç®¡

-0.14

osta

-0.14

-0.13

POSITIVE LOGITS

embre

0.16

RIA

0.14

leaf

0.13

 Farr

0.13

ato

0.13

 Cole

0.13

 Dash

0.13

 Chang

0.13

 Char

0.13

fusion

0.13

Activations Density 0.559%

dialogue and conversational structures within text

No Comments

No Known Activations