INDEX

Explanations

gerunds and words related to roles and actions in a structured context

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

ings

-0.23

guns

-0.18

ality

-0.16

lt

-0.16

ng

-0.15

zb

-0.15

xs

-0.15

zh

-0.15

oul

-0.15

iw

-0.15

POSITIVE LOGITS

 factor

0.26

 factors

0.25

redient

0.23

redients

0.22

factor

0.22

 Factors

0.21

-factor

0.20

 Factor

0.19

_FACTOR

0.18

 force

0.18

Activations Density 0.142%

gerunds and words related to roles and actions in a structured context

No Comments

No Known Activations