INDEX

Explanations

references to "Home" as a concept or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

stal

-0.18

neau

-0.18

 Blasio

-0.17

ivec

-0.16

êµ´

-0.15

sei

-0.14

Ã¤h

-0.14

smarty

-0.14

sta

-0.14

adas

-0.13

POSITIVE LOGITS

opathic

0.25

coming

0.24

brew

0.23

unc

0.20

grown

0.20

comings

0.20

opathy

0.19

omorphic

0.18

opath

0.18

lessness

0.18

Activations Density 0.007%

references to "Home" as a concept or location

No Comments

No Known Activations