INDEX

Explanations

key entities and terms related to organizations, governmental bodies, and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

fty

-0.16

ACITY

-0.14

ãĥĶãĥ¼

-0.14

$LANG

-0.14

adol

-0.13

 Ulus

-0.13

_|

-0.13

 GetEnumerator

-0.13

undra

-0.13

ÐºÐ¾Ð¿

-0.12

POSITIVE LOGITS

âĢħ

0.15

oretical

0.15

[âĢ¦

0.13

 township

0.13

URRENT

0.13

ostel

0.12

ÃŃses

0.12

inas

0.12

ombat

0.12

 WithEvents

0.12

Activations Density 0.291%

key entities and terms related to organizations, governmental bodies, and medical conditions

No Comments

No Known Activations