INDEX

Explanations

references to heists or theft-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

éĶĭ

-0.15

elsen

-0.14

 Dá»¯

-0.14

ruba

-0.14

Intermediate

-0.14

onnement

-0.14

onso

-0.14

ieres

-0.14

 Swap

-0.14

apple

-0.14

POSITIVE LOGITS

 Bond

0.17

Bond

0.16

*pow

0.15

 extra

0.14

andler

0.14

-Agent

0.14

Tier

0.14

 agencies

0.14

 Bass

0.14

 recharge

0.13

Activations Density 0.334%

references to heists or theft-related activities

No Comments

No Known Activations