INDEX

Explanations

mentions of specific statistics or quantitative measurements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iete

-0.15

iele

-0.15

 Defender

-0.15

.Sdk

-0.14

esc

-0.14

cli

-0.14

 Pike

-0.14

 Memphis

-0.13

 germ

-0.13

nh

-0.13

POSITIVE LOGITS

enas

0.17

gaard

0.16

ÙĪØ²

0.14

Ú¯Ø§ÙĨÛĮ

0.14

 material

0.14

ÙĪØ²ÛĮ

0.14

opis

0.14

wald

0.14

 Millenn

0.14

Seq

0.14

Activations Density 0.083%

mentions of specific statistics or quantitative measurements

No Comments

No Known Activations