INDEX

Explanations

repeated mentions of the word "Houston."

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

old

-0.15

aul

-0.15

eton

-0.14

older

-0.14

 Birch

-0.14

ergus

-0.13

uchi

-0.13

 clot

-0.13

ELLOW

-0.13

inux

-0.13

POSITIVE LOGITS

obl

0.16

uario

0.15

baugh

0.15

ailer

0.14

ãĥ³ãĥķ

0.14

 Relief

0.14

adera

0.14

 Ende

0.14

uC

0.14

rov

0.14

Activations Density 0.009%

repeated mentions of the word "Houston."

No Comments

No Known Activations