INDEX

Explanations

references to significant actions or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã¤nger

-0.16

idis

-0.16

ify

-0.15

.sg

-0.15

vrd

-0.14

 besides

-0.14

orean

-0.14

Å¡et

-0.14

[:]

-0.13

.Db

-0.13

POSITIVE LOGITS

 involving

0.21

0.16

é£¯

0.15

anc

0.14

PackageManager

0.14

iyim

0.14

 surrounding

0.14

esser

0.14

/moment

0.13

fon

0.13

Activations Density 0.016%

references to significant actions or occurrences

No Comments

No Known Activations