INDEX

Explanations

numeric representations and formatting

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

imer

-0.16

arias

-0.15

erre

-0.15

ooky

-0.15

eren

-0.15

ernen

-0.14

.li

-0.14

.broadcast

-0.14

Ł³

-0.14

POSITIVE LOGITS

.scalablytyped

0.16

_AUX

0.15

 wiki

0.14

TURE

0.14

lean

0.14

eya

0.14

abol

0.14

 Rifle

0.13

 directional

0.13

 Ø·Ø±

0.13

Activations Density 0.004%

numeric representations and formatting

No Comments

No Known Activations