INDEX

Explanations

statements related to legal and procedural validations

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

kowski

-0.17

cus

-0.15

adam

-0.14

Ð°Ð¹ÑĤ

-0.14

eb

-0.14

ois

-0.14

oggler

-0.14

Ð¼ÐµÑĩ

-0.14

otto

-0.14

POSITIVE LOGITS

Sno

0.15

_singleton

0.15

erset

0.14

irie

0.14

avras

0.14

Ð»Ð»

0.14

secs

0.13

mul

0.13

 partida

0.13

iece

0.13

Activations Density 0.290%

statements related to legal and procedural validations

No Comments

No Known Activations