INDEX

Explanations

keywords related to programming functions and variable declarations

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

arb

-0.15

æ´

-0.15

lector

-0.14

hlas

-0.14

zone

-0.14

dj

-0.14

iner

-0.14

ar

-0.14

 æ´

-0.13

Baz

-0.13

POSITIVE LOGITS

iless

0.17

egasus

0.15

æĻ¶

0.14

kip

0.14

udder

0.14

.scala

0.14

orne

0.14

Ä±ÅŁÄ±k

0.13

Activations Density 0.009%

keywords related to programming functions and variable declarations

No Comments

No Known Activations