INDEX

Explanations

occurrences of the name "Tom" 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 @ 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

iaux

-0.18

ãĥĭãĤ¢

-0.17

erte

-0.17

ÑĪÑĤ

-0.16

uela

-0.16

vet

-0.16

uary

-0.16

stadt

-0.15

ABLE

-0.15

weep

-0.15

POSITIVE LOGITS

Tom

0.30

tom

0.28

atoes

0.28

orrow

0.27

asz

0.24

tom

0.24

islav

0.24

kins

0.23

cat

0.23

cats

0.23

Activations Density 0.017%

occurrences of the name "Tom" in various contexts

No Comments

No Known Activations