INDEX

Explanations

phrases indicating official acknowledgment or declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

olla

-0.17

iang

-0.15

fs

-0.15

MainFrame

-0.15

OTO

-0.14

Ħ

-0.14

strain

-0.14

ivot

-0.14

POSITIVE LOGITS

 Affero

0.18

å®Ļ

0.15

 Knife

0.15

isseur

0.15

ecz

0.15

itoris

0.14

DS

0.14

apesh

0.14

uido

0.14

entina

0.14

Activations Density 0.039%

phrases indicating official acknowledgment or declarations

No Comments

No Known Activations