INDEX

Explanations

terms related to matching and selectors in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ŀ

-0.15

gow

-0.15

ZD

-0.14

.gridColumn

-0.14

ingham

-0.14

$__

-0.14

ãĥ¼ãĥ¬

-0.14

kn

-0.14

ey

-0.13

ëŀĮ

-0.13

POSITIVE LOGITS

0.18

.bean

0.15

chas

0.15

/commons

0.15

osex

0.14

ograd

0.14

Ð¼ÐµÑĢ

0.14

0.13

ily

0.13

Activations Density 0.001%

terms related to matching and selectors in programming contexts

No Comments

No Known Activations