INDEX

Explanations

details related to measurements and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

okud

-0.16

ombo

-0.15

ceb

-0.15

allee

-0.14

UNT

-0.14

 dozens

-0.13

atÃŃm

-0.13

teenth

-0.12

inth

-0.12

ozem

-0.12

POSITIVE LOGITS

0.34

0.18

0.17

0.16

Activations Density 0.836%

details related to measurements and specifications

No Comments

No Known Activations