INDEX

Explanations

references to hidden or concealed locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

imus

-0.18

ustum

-0.15

imento

-0.15

ãĥ³ãĥ

-0.15

encer

-0.14

ricanes

-0.14

isce

-0.14

.utf

-0.14

agini

-0.14

POSITIVE LOGITS

sx

0.15

esper

0.14

inch

0.14

 Airways

0.14

ingham

0.14

scale

0.14

Ð¾Ð´Ð°Ð²

0.13

_Util

0.13

 chá»§

0.13

Desk

0.13

Activations Density 0.034%

references to hidden or concealed locations

No Comments

No Known Activations