INDEX

Explanations

elements that represent structured data or components in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

igin

-0.16

ToDevice

-0.15

Ð¼ÑĸÐ½

-0.15

Fcn

-0.15

çłĤ

-0.14

oes

-0.14

_parms

-0.14

âĶ£

-0.14

_FILENO

-0.14

.tie

-0.14

POSITIVE LOGITS

 *↵

0.17

^^^^

0.15

var

0.15

 Late

0.14

srv

0.14

fl

0.14

abei

0.14

 Holl

0.14

0.13

Hir

0.13

Activations Density 0.013%

elements that represent structured data or components in a programming context

No Comments

No Known Activations