INDEX

Explanations

references to locations, particularly cities related to political or community contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tems

-0.16

alf

-0.15

Ãłi

-0.15

uldu

-0.14

 Cors

-0.14

 Guth

-0.14

riel

-0.14

hest

-0.13

ÃŃrk

-0.13

/Resources

-0.13

POSITIVE LOGITS

abox

0.16

APPER

0.15

vier

0.15

íĮħ

0.15

rippling

0.15

aley

0.15

ë¹

0.14

ilio

0.14

Î³Î®

0.14

isco

0.14

Activations Density 0.001%

references to locations, particularly cities related to political or community contexts

No Comments

No Known Activations