INDEX

Explanations

mentions of academic or government department names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ilon

-0.15

conversation

-0.14

çľī

-0.14

lya

-0.14

áºŃt

-0.14

plib

-0.14

 Reyn

-0.13

sid

-0.13

 conversation

-0.13

anship

-0.13

POSITIVE LOGITS

íĻĺ

0.14

nÃŃky

0.14

ADED

0.14

.variables

0.14

.singleton

0.14

ainen

0.14

egasus

0.14

ÅĻiv

0.13

å¸¯

0.13

xis

0.13

Activations Density 0.017%

mentions of academic or government department names

No Comments

No Known Activations