INDEX

Explanations

code constructs related to hash functions and their calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

.truth

-0.15

etto

-0.15

bsolute

-0.14

Å¾il

-0.14

alla

-0.14

dur

-0.14

dem

-0.14

oods

-0.14

allas

-0.14

DM

-0.14

POSITIVE LOGITS

hashCode

0.27

 hashCode

0.24

.hashCode

0.23

 prime

0.22

 Hash

0.21

prime

0.21

HashCode

0.20

0.19

 hash

0.19

 HASH

0.19

Activations Density 0.016%

code constructs related to hash functions and their calculations

No Comments

No Known Activations