INDEX

Explanations

elements related to cleverness or intelligence, particularly in language and writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

hand

-0.24

ho

-0.21

hide

-0.20

hold

-0.20

haft

-0.20

erif

-0.20

hood

-0.19

hip

-0.19

hol

-0.19

hit

-0.19

POSITIVE LOGITS

ting

0.60

ted

0.44

ters

0.38

tings

0.37

TING

0.34

ten

0.30

tingham

0.28

ãģĬãĤĬ

0.28

ropolis

0.27

tle

0.25

Activations Density 1.004%

elements related to cleverness or intelligence, particularly in language and writing

No Comments

No Known Activations