INDEX

Explanations

references to ships and nautical themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

leh

-0.15

 Held

-0.14

 Nile

-0.14

æºª

-0.13

íķ©

-0.13

uisse

-0.13

ÏĢÎ»Î±

-0.13

adele

-0.13

ç¸

-0.13

POSITIVE LOGITS

ighthouse

0.31

0.28

 tower

0.27

çģ¯

0.26

 keeper

0.25

 Light

0.25

 light

0.24

 beacon

0.24

elight

0.23

 LIGHT

0.22

Activations Density 0.020%

references to ships and nautical themes

No Comments

No Known Activations