INDEX

Explanations

programming terms related to data input and handling in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 polar

-0.15

stal

-0.15

rig

-0.15

otos

-0.15

rn

-0.14

rig

-0.14

outs

-0.14

uge

-0.14

esign

-0.14

Eug

-0.14

POSITIVE LOGITS

pedia

0.18

zik

0.17

ì¸µ

0.16

ÄĽti

0.15

itness

0.14

Å¯vod

0.14

chedulers

0.14

ÐĿÐĨ

0.14

obili

0.14

ORMAT

0.14

Activations Density 0.040%

programming terms related to data input and handling in code

No Comments

No Known Activations