INDEX

Explanations

Modal verbs indicating possibility or necessity

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

ilor

-0.16

arias

-0.15

urt

-0.15

alian

-0.14

ke

-0.14

ylie

-0.14

iris

-0.13

alia

-0.13

yst

-0.13

POSITIVE LOGITS

ville

0.16

bach

0.16

ĳ

0.15

abolic

0.15

ase

0.15

vay

0.14

ê°¤

0.14

Coeff

0.14

zelf

0.14

Stamp

0.14

Activations Density 0.117%

Modal verbs indicating possibility or necessity

No Comments

No Known Activations