INDEX

Explanations

key terms related to events and activities

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

agas

-0.18

peri

-0.17

 Bone

-0.16

olini

-0.16

iesen

-0.15

ungs

-0.15

ONSE

-0.15

Bone

-0.14

arkin

-0.14

POSITIVE LOGITS

Blog

0.15

nit

0.14

 Ville

0.14

ant

0.14

deo

0.14

0.13

antino

0.13

INDOW

0.13

_launcher

0.13

yat

0.13

Activations Density 0.000%

key terms related to events and activities

No Comments

No Known Activations