INDEX

Explanations

specific identifiers and phrases related to definitions and explanations

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

uby

-0.16

lexport

-0.15

amo

-0.15

irit

-0.15

Ãºde

-0.14

uyá»ĩt

-0.14

cken

-0.14

ccoli

-0.14

aign

-0.14

odesk

-0.14

POSITIVE LOGITS

 this

0.17

0.15

 cine

0.14

 ÑįÑĤÐ¾

0.14

 here

0.14

amp

0.14

 uintptr

0.14

 This

0.14

 term

0.14

Activations Density 0.160%

specific identifiers and phrases related to definitions and explanations

No Comments

No Known Activations