INDEX

Explanations

references to TensorFlow and its functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

orta

-0.18

vak

-0.18

usta

-0.17

amina

-0.16

ENDER

-0.15

uta

-0.15

ense

-0.15

msp

-0.14

erno

-0.14

POSITIVE LOGITS

ylation

0.15

_thumb

0.15

_tpl

0.15

igsaw

0.14

etrofit

0.14

 beri

0.14

Ð¸Ð¼Ð²

0.14

hardt

0.14

iel

0.14

ive

0.13

Activations Density 0.001%

references to TensorFlow and its functionalities

No Comments

No Known Activations