INDEX

Explanations

terms related to geographical locations or administrative boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

altar

-0.15

azzi

-0.15

_library

-0.14

ennie

-0.14

 trick

-0.14

ton

-0.13

DCF

-0.13

 gran

-0.13

 junior

-0.13

Ã©nÃ©

-0.13

POSITIVE LOGITS

YLE

0.15

fty

0.15

ameda

0.14

-www

0.14

æŃ£

0.14

uty

0.14

à¸´à¸ķà¸£

0.14

Ð²Ð°Ð»

0.13

-carousel

0.13

 Monthly

0.13

Activations Density 0.095%

terms related to geographical locations or administrative boundaries

No Comments

No Known Activations