INDEX

Explanations

references to specific locations and their roles within a structure or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

UGH

-0.15

ugas

-0.15

aker

-0.15

OSH

-0.15

¿

-0.14

leep

-0.14

Ã¶h

-0.14

tub

-0.14

agra

-0.14

Ð¾Ð¶ÐµÑĤ

-0.13

POSITIVE LOGITS

 footer

0.16

 header

0.16

header

0.16

lasÄ±

0.15

 spare

0.15

Ã¡bado

0.15

inalg

0.15

 each

0.14

antly

0.14

_misc

0.14

Activations Density 0.253%

references to specific locations and their roles within a structure or organization

No Comments

No Known Activations