INDEX

Explanations

concepts related to critiques and discussions of social norms or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

(æĹ¥

-0.18

aska

-0.18

ãĥĭãĤ¢

-0.17

edback

-0.15

ÑĢÐ¾Ð¿

-0.15

ropp

-0.14

ervers

-0.14

lesc

-0.14

panied

-0.14

POSITIVE LOGITS

par

0.51

par

0.35

 extra

0.34

Par

0.31

.par

0.28

-par

0.27

_par

0.26

 Extra

0.26

 supreme

0.26

extra

0.24

Activations Density 0.116%

concepts related to critiques and discussions of social norms or attributes

No Comments

No Known Activations