INDEX

Explanations

references to programming terms related to functions and event handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lea

-0.16

INDER

-0.15

lox

-0.14

resas

-0.14

 NavParams

-0.14

ÐµÑģÑĤ

-0.14

 himself

-0.13

alue

-0.13

inder

-0.13

POSITIVE LOGITS

arella

0.16

zyst

0.16

ingly

0.15

Ø®ØµÙĪØµ

0.15

æķ

0.15

buster

0.15

orre

0.15

 halinde

0.15

arty

0.14

adan

0.14

Activations Density 0.323%

references to programming terms related to functions and event handling

No Comments

No Known Activations