INDEX

Explanations

specific measurements or dimensions related to artworks or prints

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

IPH

-0.16

ious

-0.15

 Burr

-0.15

 æ¹

-0.14

IOUS

-0.14

idon

-0.14

 Tyson

-0.14

ascus

-0.14

ÑĤÑĭÐ¹

-0.14

ingham

-0.14

POSITIVE LOGITS

emm

0.16

rette

0.16

 anale

0.15

orse

0.14

 facto

0.14

 obce

0.14

\Module

0.13

aad

0.13

adh

0.13

 Twitch

0.13

Activations Density 0.010%

specific measurements or dimensions related to artworks or prints

No Comments

No Known Activations