INDEX

Explanations

references to philosophical concepts and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

UX

-0.16

indr

-0.16

vertex

-0.14

neider

-0.14

ä¾Ľ

-0.14

ulo

-0.14

atu

-0.13

eki

-0.13

Ð³Ð¾Ð²

-0.13

POSITIVE LOGITS

ocker

0.16

Compat

0.15

 Bucc

0.14

 sire

0.14

 Said

0.13

jiang

0.13

$MESS

0.13

_initializer

0.13

apon

0.13

(__

0.13

Activations Density 0.162%

references to philosophical concepts and arguments

No Comments

No Known Activations