INDEX

Explanations

technical terminology and mathematical expressions related to loops and responses

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ieg

-0.17

vens

-0.15

ecta

-0.14

ecl

-0.14

onom

-0.14

Ð¸Ð¸

-0.14

dzi

-0.14

ContentPane

-0.13

awei

-0.13

 Ð·Ð°Ð»

-0.13

POSITIVE LOGITS

learner

0.15

ewood

0.15

lash

0.15

_INF

0.14

 stati

0.14

 Trev

0.14

midd

0.14

 Vivo

0.13

dux

0.13

 Emer

0.13

Activations Density 0.043%

technical terminology and mathematical expressions related to loops and responses

No Comments

No Known Activations