INDEX

Explanations

information and references regarding tickets, related materials, and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iphy

-0.16

arella

-0.16

.Bot

-0.15

 addCriterion

-0.15

ickers

-0.15

eya

-0.15

adder

-0.15

ivre

-0.15

aban

-0.14

CodeGen

-0.14

POSITIVE LOGITS

Ļ

0.16

mental

0.16

0.15

åĩ

0.15

 Wein

0.15

 Bros

0.14

CC

0.14

idos

0.14

Ð¾Ñī

0.14

SB

0.14

Activations Density 0.210%

information and references regarding tickets, related materials, and documentation

No Comments

No Known Activations