INDEX

Explanations

terms related to auditions and performance opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

EDIA

-0.17

ctic

-0.16

ponent

-0.16

opoulos

-0.15

unic

-0.15

oice

-0.15

eenth

-0.14

éĥİ

-0.14

ëĵł

-0.14

OAD

-0.14

POSITIVE LOGITS

rey

0.21

arya

0.20

ium

0.18

rys

0.17

olph

0.15

wen

0.15

Aud

0.15

erdale

0.15

ible

0.15

aud

0.15

Activations Density 0.016%

terms related to auditions and performance opportunities

No Comments

No Known Activations