INDEX

Explanations

occurrences of the letter "D" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

EDIATE

-0.17

Äįer

-0.16

uso

-0.15

PTH

-0.15

ecast

-0.15

-0.14

åħ¸

-0.14

åĬŁ

-0.14

ibur

-0.14

POSITIVE LOGITS

ems

0.26

em

0.23

HS

0.19

ism

0.19

ereg

0.19

him

0.19

oping

0.19

angers

0.18

eter

0.18

pty

0.18

Activations Density 0.025%

occurrences of the letter "D" in various contexts

No Comments

No Known Activations