INDEX

Explanations

terms related to various types of products and goods

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

Ð°Ð±Ð»Ð¸ÑĨ

-0.15

adder

-0.15

eg

-0.15

aler

-0.14

hani

-0.14

lr

-0.14

hoff

-0.14

plib

-0.13

onom

-0.13

en

-0.13

POSITIVE LOGITS

zes

0.17

auga

0.15

uchar

0.14

_OBJC

0.14

TEE

0.14

bÃŃ

0.14

indsight

0.14

ringe

0.14

iglia

0.13

 adel

0.13

Activations Density 0.027%

terms related to various types of products and goods

No Comments

No Known Activations