INDEX

Explanations

references to programming documentation and file types

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

á»ĵn

-0.17

orta

-0.16

iggers

-0.15

wares

-0.14

 Ð¿ÑĢÐ¾Ñģ

-0.14

ÐºÑĤÐ°

-0.14

ÎµÎ¹ÏĤ

-0.14

nbr

-0.13

_extend

-0.13

į°

-0.13

POSITIVE LOGITS

 Advent

0.15

0.14

antar

0.14

 INLINE

0.13

 undergraduate

0.13

ody

0.13

Pil

0.13

 Institutes

0.13

list

0.13

 tang

0.13

Activations Density 0.001%

references to programming documentation and file types

No Comments

No Known Activations