INDEX

Explanations

references to geographical locations or administrative regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

"label

-0.17

enha

-0.16

ConnectionFactory

-0.15

atern

-0.14

imat

-0.14

rieg

-0.14

ÏĥÏĦÎµ

-0.14

 COPYING

-0.13

rary

-0.13

erus

-0.13

POSITIVE LOGITS

 walls

0.15

/out

0.14

ê±´

0.14

 bounds

0.14

walls

0.14

opup

0.13

addle

0.13

 Walls

0.13

per

0.13

Activations Density 0.032%

references to geographical locations or administrative regions

No Comments

No Known Activations