INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

bjerg

-0.15

áº¡n

-0.14

inger

-0.14

yum

-0.14

oS

-0.14

ble

-0.14

-0.13

arters

-0.13

Ð¶Ðµ

-0.13

ters

-0.13

POSITIVE LOGITS

Nob

0.17

ehr

0.16

Ā

0.15

(æľ¨

0.14

èĹ

0.14

(æĹ¥

0.14

-keys

0.13

onda

0.13

 localVar

0.13

.scalablytyped

0.13

Activations Density 0.061%

numerical data or statistics

No Comments

No Known Activations