INDEX

Explanations

specific categories and metrics related to measurements, sports statistics, and classifications

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

.instant

-0.18

ummer

-0.16

eka

-0.16

erken

-0.16

arrera

-0.16

ahan

-0.15

ä¿

-0.15

ogl

-0.15

ÑıÐ½

-0.15

.Syntax

-0.14

POSITIVE LOGITS

0.19

 broad

0.16

(s

0.16

atk

0.15

atum

0.14

alt

0.14

gra

0.14

BBB

0.14

 Mild

0.14

Hun

0.14

Activations Density 0.107%

specific categories and metrics related to measurements, sports statistics, and classifications

No Comments

No Known Activations