INDEX

Explanations

mentions of "Columbia" and "Columbia University."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

;element

-0.14

landa

-0.14

aises

-0.14

_Impl

-0.14

abal

-0.14

rap

-0.14

iminal

-0.14

aben

-0.14

ement

-0.13

POSITIVE LOGITS

 Pictures

0.23

Pictures

0.20

 Columbia

0.16

pictures

0.16

hed

0.16

istro

0.15

olumbia

0.15

 pictures

0.15

ency

0.15

ale

0.15

Activations Density 0.007%

mentions of "Columbia" and "Columbia University."

No Comments

No Known Activations