INDEX

Explanations

modal verbs expressing ability or permission

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tere

-0.16

egment

-0.15

owards

-0.15

_PRINTF

-0.15

amac

-0.15

acer

-0.14

deo

-0.14

abbo

-0.14

enie

-0.14

à¥įà¤°à¤¥

-0.14

POSITIVE LOGITS

ConfigurationException

0.17

sel

0.17

otropic

0.15

base

0.14

bon

0.14

dale

0.14

unte

0.13

aine

0.13

uf

0.13

 comb

0.13

Activations Density 0.172%

modal verbs expressing ability or permission

No Comments

No Known Activations