INDEX

Explanations

phrases indicating documentation or record-keeping actions related to accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ipay

-0.15

unga

-0.15

phinx

-0.14

enville

-0.14

Ã¹

-0.14

DW

-0.14

ported

-0.14

mium

-0.13

hya

-0.13

yx

-0.13

POSITIVE LOGITS

ertz

0.17

resh

0.14

Î¬Î²

0.14

Ð°ÑĤÑĸ

0.13

à¸²à¸¥

0.13

Ted

0.13

raquo

0.13

|_|

0.13

GEST

0.13

orton

0.12

Activations Density 0.165%

phrases indicating documentation or record-keeping actions related to accountability

No Comments

No Known Activations