INDEX

Explanations

temporal indicators and references to specific time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

elper

-0.18

itos

-0.15

endum

-0.14

urs

-0.14

/dashboard

-0.14

IMS

-0.14

wers

-0.14

ubar

-0.13

outube

-0.13

 ÑģÑħÐ¾Ð´

-0.13

POSITIVE LOGITS

0.16

enant

0.14

agem

0.14

ilib

0.14

 accom

0.14

ovol

0.14

eri

0.14

 Beetle

0.13

 gÃ¶tÃ¼r

0.13

Activations Density 0.090%

temporal indicators and references to specific time periods

No Comments

No Known Activations