INDEX

Explanations

references to years and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

jac

-0.17

uisse

-0.15

unj

-0.15

zech

-0.14

Û²Û°Û²

-0.14

ÃľRK

-0.14

_CAM

-0.14

asio

-0.14

Ã¤h

-0.13

ÃŃsto

-0.13

POSITIVE LOGITS

0.22

0.16

ainers

0.14

0.13

acock

0.13

âĤĢ

0.13

Activations Density 0.221%

references to years and dates

No Comments

No Known Activations