INDEX

Explanations

mathematical expressions and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ser

-0.17

à¤¥

-0.15

eus

-0.15

Ser

-0.15

acht

-0.15

ambia

-0.15

igram

-0.14

enso

-0.14

 Shall

-0.14

POSITIVE LOGITS

insula

0.16

nun

0.15

ãĥĬãĥ«

0.15

Subsystem

0.14

ishop

0.14

 alias

0.14

_HERSHEY

0.14

.xtext

0.14

keh

0.14

PRETTY

0.14

Activations Density 0.072%

mathematical expressions and operations

No Comments

No Known Activations