INDEX

Explanations

mentions of ranking or achievement in a competitive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

izo

-0.16

ula

-0.15

uen

-0.15

esco

-0.14

uvo

-0.14

edis

-0.14

ems

-0.14

cum

-0.13

etal

-0.13

izi

-0.13

POSITIVE LOGITS

Thy

0.16

OTES

0.16

.usermodel

0.15

è¡¡

0.15

olon

0.14

.listFiles

0.14

arga

0.14

orth

0.14

 vign

0.14

ÌĨ

0.14

Activations Density 0.036%

mentions of ranking or achievement in a competitive context

No Comments

No Known Activations