INDEX

Explanations

references to religious symbols and deities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Mob

-0.15

ç±

-0.15

orian

-0.15

elden

-0.15

quito

-0.14

ÙģÙĤ

-0.14

ilde

-0.14

pike

-0.14

Ð¶Ñĥ

-0.14

 kent

-0.14

POSITIVE LOGITS

 sway

0.21

 Lord

0.20

Bra

0.20

 Ling

0.20

 ling

0.19

Sw

0.19

Dev

0.19

 Tray

0.18

Lord

0.18

 Trim

0.18

Activations Density 0.253%

references to religious symbols and deities

No Comments

No Known Activations