INDEX

Explanations

proper nouns related to people and TV shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

vido

-0.15

 versions

-0.14

wel

-0.14

ooled

-0.13

eder

-0.13

utter

-0.13

die

-0.13

.Dispatcher

-0.13

obbies

-0.13

POSITIVE LOGITS

aleigh

0.16

ToDevice

0.15

 ë¶Ħ

0.15

ìĤ¬ë¬´

0.15

.SDK

0.14

kea

0.14

StringRef

0.14

ignet

0.14

istrovstvÃŃ

0.14

ModifiedDate

0.13

Activations Density 0.026%

proper nouns related to people and TV shows

No Comments

No Known Activations