INDEX

Explanations

numerical values and measurements related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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°ÑĪÐ°

-0.14

bai

-0.14

cip

-0.13

 nominate

-0.13

 Frid

-0.13

uby

-0.13

_Utils

-0.13

è¥²

-0.13

ê½

-0.13

Cad

-0.13

POSITIVE LOGITS

 depending

0.23

depending

0.21

 Depending

0.15

ilar

0.15

agog

0.15

@testable

0.15

Depending

0.14

ients

0.14

 ÎĴÎ±

0.14

strict

0.14

Activations Density 0.048%

numerical values and measurements related to various contexts

No Comments

No Known Activations