INDEX

Explanations

references to significant entities or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÑĥÑĢÑģ

-0.17

ÏģÏīÎ½

-0.15

wright

-0.15

LAT

-0.14

ward

-0.14

raison

-0.14

 prospect

-0.14

>tag

-0.13

 èı

-0.13

leigh

-0.13

POSITIVE LOGITS

ivery

0.17

æ´¥

0.16

ught

0.16

tar

0.15

 concern

0.15

 magnitude

0.15

HL

0.14

magnitude

0.14

tat

0.14

 Draco

0.14

Activations Density 0.111%

references to significant entities or themes

No Comments

No Known Activations