INDEX

Explanations

colons that introduce categories or tags

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

uml

-0.19

mund

-0.18

istrovstvÃŃ

-0.17

ÑĢÐ°Ðº

-0.17

-ts

-0.16

itre

-0.16

uder

-0.15

volution

-0.14

 éĹ

-0.14

nil

-0.14

POSITIVE LOGITS

Ĺ

0.16

0.14

_orient

0.13

aceous

0.13

 Harmon

0.13

_physical

0.13

Ta

0.13

CEL

0.13

 packing

0.13

Activations Density 0.001%

colons that introduce categories or tags

No Comments

No Known Activations