INDEX

Explanations

names and locations related to criminal activities or legal cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

lz

-0.16

 neutron

-0.16

Ø§Ø¦ÙĦ

-0.15

isay

-0.15

reck

-0.15

ivy

-0.15

ervas

-0.15

atz

-0.14

ourg

-0.14

 Beng

-0.14

POSITIVE LOGITS

 Delta

0.16

 Bunu

0.15

Delta

0.15

 paramount

0.15

mouseup

0.15

Ih

0.14

erin

0.14

 internally

0.14

chter

0.14

_capabilities

0.14

Activations Density 0.042%

names and locations related to criminal activities or legal cases

No Comments

No Known Activations