INDEX

Explanations

terms related to statistical measurements and data analysis

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

ÑĤÐµÐ½

-0.15

 Ekim

-0.15

.Std

-0.15

 moci

-0.14

ãĥ³ãĥĹ

-0.14

aign

-0.14

/sdk

-0.13

noise

-0.13

 Pitch

-0.13

ëĤł

-0.13

POSITIVE LOGITS

elerik

0.17

0.15

fcn

0.15

wheel

0.14

aye

0.14

eler

0.14

izzo

0.14

.setResult

0.14

scal

0.14

çļ

0.14

Activations Density 0.337%

terms related to statistical measurements and data analysis

No Comments

No Known Activations