INDEX

Explanations

information about events, details, and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.14

esome

-0.14

glob

-0.14

assage

-0.14

andin

-0.13

zim

-0.13

æĶ

-0.13

roup

-0.13

ocal

-0.13

ifest

-0.13

POSITIVE LOGITS

 yourself

0.19

 Yourself

0.15

Î½Î¿Î¼

0.15

 nhÃ©

0.14

hta

0.14

 yourselves

0.13

arken

0.13

Wax

0.13

à¸ļà¸Ħ

0.13

ÙģØ³

0.13

Activations Density 0.152%

information about events, details, and inquiries

No Comments

No Known Activations