INDEX

Explanations

words related to specific numeric identifiers or codes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eki

-0.16

igi

-0.16

lexport

-0.16

aklÄ±

-0.14

escort

-0.14

.Lang

-0.13

eryl

-0.13

ÏģÎ¹ÏĥÏĦ

-0.13

 Nunes

-0.13

ÐµÑĢÐº

-0.13

POSITIVE LOGITS

dle

0.15

oodoo

0.14

ollo

0.14

æĬĺ

0.14

lings

0.14

 VerfÃ¼gung

0.14

Ð¸Ð¼Ð¾

0.14

atasets

0.14

RetVal

0.13

tar

0.13

Activations Density 0.012%

words related to specific numeric identifiers or codes

No Comments

No Known Activations