INDEX

Explanations

lines of code or references to specific methods and their execution within test frameworks

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

vala

-0.17

isas

-0.15

pios

-0.14

ilenames

-0.14

omas

-0.14

jabi

-0.14

ecer

-0.14

å¤§äºº

-0.14

OOT

-0.14

ãĥ³ãĥģ

-0.14

POSITIVE LOGITS

airy

0.14

orate

0.14

.INTERNAL

0.14

conomy

0.13

.dispatcher

0.13

Sk

0.13

RU

0.13

ìĩ¼

0.13

 Riders

0.13

uy

0.13

Activations Density 0.018%

lines of code or references to specific methods and their execution within test frameworks

No Comments

No Known Activations