INDEX

Explanations

terms related to software development and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

_sdk

-0.17

acz

-0.17

apus

-0.15

³

-0.15

increment

-0.15

iat

-0.14

ç»ı

-0.14

_oauth

-0.14

ł

-0.14

 QLatin

-0.14

POSITIVE LOGITS

ãĥ¼ãĥ³

0.16

æĸ¹

0.16

 æĸ¹

0.15

dee

0.14

forme

0.14

poss

0.14

 POSSIBILITY

0.14

Ðĩ

0.14

oso

0.13

.ms

0.13

Activations Density 0.033%

terms related to software development and code structure

No Comments

No Known Activations