INDEX

Explanations

modal verbs indicating possibility or ability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rick

-0.15

#__

-0.15

worth

-0.14

sworth

-0.14

ognito

-0.14

lla

-0.13

ige

-0.13

.ide

-0.13

ndef

-0.13

iskey

-0.13

POSITIVE LOGITS

lander

0.17

0.15

0.14

jin

0.14

deme

0.14

jon

0.14

mium

0.14

itr

0.14

.showMessage

0.14

Activations Density 0.045%

modal verbs indicating possibility or ability

No Comments

No Known Activations