INDEX

Explanations

questions or inquiries regarding processes and instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

avage

-0.17

orre

-0.17

ippo

-0.16

uent

-0.15

ned

-0.15

arro

-0.15

wayne

-0.15

ASTER

-0.15

isure

-0.14

.timeScale

-0.14

POSITIVE LOGITS

itz

0.23

itzer

0.23

beit

0.22

ells

0.21

arth

0.21

ARD

0.20

soever

0.20

ards

0.19

lett

0.19

ick

0.19

Activations Density 0.035%

questions or inquiries regarding processes and instructions

No Comments

No Known Activations