INDEX

Explanations

references to specific cities, especially their names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

dit

-0.16

nox

-0.15

ders

-0.15

Î´ÏģÎ±

-0.15

ylene

-0.14

izzard

-0.14

riott

-0.14

ding

-0.14

edy

-0.14

idon

-0.14

POSITIVE LOGITS

esion

0.15

Hib

0.14

agh

0.14

ruh

0.14

ActionBar

0.14

å

0.14

eref

0.14

iona

0.14

asin

0.13

McL

0.13

Activations Density 0.011%

references to specific cities, especially their names

No Comments

No Known Activations