INDEX

Explanations

statements expressing observation or perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

isi

-0.15

unt

-0.14

ãĥ¼ãĤº

-0.14

Ø±ÙĬÙĥ

-0.14

oret

-0.14

uta

-0.14

uss

-0.14

udu

-0.13

atsu

-0.13

asc

-0.13

POSITIVE LOGITS

 evidence

0.21

 Evidence

0.18

 plenty

0.17

/he

0.17

Evidence

0.16

Unnamed

0.16

ohana

0.15

 lots

0.15

him

0.15

how

0.15

Activations Density 0.127%

statements expressing observation or perception

No Comments

No Known Activations