INDEX

Explanations

patterns related to specific phrases or entities that might indicate a cultural or regional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.16

ox

-0.16

quare

-0.15

rael

-0.15

 Berger

-0.15

hs

-0.15

emas

-0.14

imary

-0.14

ucht

-0.14

js

-0.14

POSITIVE LOGITS

led

0.17

ude

0.17

usz

0.15

vic

0.14

ÏģÎ¿

0.14

hari

0.14

 Springs

0.14

adia

0.14

Zug

0.14

º

0.14

Activations Density 0.013%

patterns related to specific phrases or entities that might indicate a cultural or regional context

No Comments

No Known Activations