INDEX

Explanations

instances of the word "or."

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

 vice

-0.20

ascus

-0.16

 Vice

-0.16

 otherwise

-0.16

 Graz

-0.15

.win

-0.15

atin

-0.15

otherwise

-0.15

vice

-0.14

Bes

-0.14

POSITIVE LOGITS

aska

0.17

 beyond

0.15

isas

0.15

ogg

0.14

 Islands

0.14

ikit

0.14

ÑĸÑĤÑĮ

0.14

bens

0.13

icros

0.13

apg

0.13

Activations Density 0.029%

instances of the word "or."

No Comments

No Known Activations