INDEX

Explanations

references to musical terms or jargon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

rk

-0.18

rig

-0.18

ring

-0.18

LC

-0.17

ibia

-0.17

riz

-0.16

rak

-0.16

uke

-0.16

riger

-0.16

akt

-0.15

POSITIVE LOGITS

ues

0.28

ilded

0.24

he

0.22

ourmet

0.21

hee

0.20

ued

0.19

ird

0.19

hey

0.19

raft

0.19

opher

0.19

Activations Density 0.231%

references to musical terms or jargon

No Comments

No Known Activations