INDEX

Explanations

references to spot-fixing incidents in cricket

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

idable

-0.15

(PC

-0.14

agina

-0.14

iyan

-0.13

snap

-0.13

 Priv

-0.13

abh

-0.13

ardon

-0.13

PCP

-0.13

POSITIVE LOGITS

 fixing

0.27

-fix

0.27

fix

0.27

 cheating

0.25

Fix

0.25

Fix

0.25

fix

0.25

 fixed

0.24

che

0.24

 FIXED

0.23

Activations Density 0.052%

references to spot-fixing incidents in cricket

No Comments

No Known Activations