INDEX

Explanations

patterns of code structure or syntax elements

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

obe

-0.16

ingle

-0.15

chop

-0.15

essler

-0.14

iera

-0.14

 patch

-0.14

 Bols

-0.14

onavir

-0.14

PRETTY

-0.14

ollen

-0.14

POSITIVE LOGITS

ctica

0.15

 opin

0.15

],&

0.14

ãĤ¿ãĥ³

0.14

kest

0.14

rove

0.14

ãĥĮ

0.14

recio

0.14

odos

0.14

lope

0.14

Activations Density 0.058%

patterns of code structure or syntax elements

No Comments

No Known Activations