INDEX

Explanations

questions and expressions of uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Daw

-0.16

uger

-0.15

 migrationBuilder

-0.15

adele

-0.15

 Legacy

-0.14

ouce

-0.14

 legacy

-0.14

 USHORT

-0.14

alle

-0.14

uries

-0.14

POSITIVE LOGITS

ultan

0.17

_CODEC

0.15

AccessType

0.15

çīĩ

0.14

antage

0.14

 Read

0.14

erk

0.14

uft

0.14

Activations Density 0.189%

questions and expressions of uncertainty

No Comments

No Known Activations