INDEX

Explanations

occurrences of the word "Sil" and its variations, indicating a focus on a specific brand or entity associated with "Sil."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tur

-0.16

quals

-0.15

 Dise

-0.14

agini

-0.14

orks

-0.14

SpaceItem

-0.14

elijke

-0.14

Ø¢

-0.14

'gc

-0.14

onders

-0.14

POSITIVE LOGITS

at

0.14

teenth

0.14

vide

0.14

idor

0.14

IDI

0.14

alia

0.13

alan

0.13

arium

0.13

iao

0.13

ernes

0.13

Activations Density 0.006%

occurrences of the word "Sil" and its variations, indicating a focus on a specific brand or entity associated with "Sil."

No Comments

No Known Activations