INDEX

Explanations

headings, titles, or categories related to events or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eer

-0.16

 tide

-0.15

ieurs

-0.14

rypto

-0.14

åĺĽ

-0.14

 relat

-0.14

ijkstra

-0.14

ampil

-0.14

ÑĩÐ¸ÑĤ

-0.14

isme

-0.14

POSITIVE LOGITS

ERRU

0.15

mlink

0.15

~~~~~~~~~~~~~~~~

0.14

 disp

0.14

ÙħØ¨Ø±

0.14

ayd

0.14

roys

0.14

orges

0.14

iams

0.13

akah

0.13

Activations Density 0.189%

headings, titles, or categories related to events or updates

No Comments

No Known Activations