INDEX

Explanations

references to specific job positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

apon

-0.17

lore

-0.17

usi

-0.17

lear

-0.16

ends

-0.15

uya

-0.15

 kond

-0.15

é¾Ħ

-0.15

opc

-0.15

wo

-0.15

POSITIVE LOGITS

ality

0.35

nement

0.34

ally

0.28

ning

0.24

naire

0.23

als

0.23

naires

0.23

nable

0.21

ned

0.20

:relative

0.20

Activations Density 0.034%

references to specific job positions

No Comments

No Known Activations