INDEX

Explanations

programming keywords and variable assignments 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĴ®

-0.16

bol

-0.16

ipple

-0.16

aises

-0.16

assis

-0.16

clid

-0.16

acyj

-0.15

 ÑĩÐ°

-0.15

venes

-0.14

edii

-0.14

POSITIVE LOGITS

aman

0.15

0.14

0.13

 doubts

0.13

HV

0.13

Geg

0.13

th

0.13

st

0.12

Activations Density 0.132%

programming keywords and variable assignments in code

No Comments

No Known Activations