INDEX

Explanations

references to religious figures and elements associated with faith

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

kel

-0.17

à¥ľ

-0.15

undra

-0.15

landscape

-0.15

((-

-0.14

agos

-0.14

pte

-0.14

kan

-0.14

pr

-0.14

POSITIVE LOGITS

WithMany

0.15

assin

0.15

Ã¡la

0.14

ojÃŃ

0.14

ÑĥÑĤÐ¸

0.14

.neo

0.14

ÙĨÚ¯ÛĮ

0.13

ripp

0.13

ì±ħ

0.13

 LÃ¢m

0.13

Activations Density 0.029%

references to religious figures and elements associated with faith

No Comments

No Known Activations