INDEX

Explanations

terms related to categorization and definition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aggio

-0.15

zion

-0.15

ardin

-0.14

iente

-0.14

enta

-0.14

Ð»ÑĥÐ³

-0.14

azzo

-0.14

iÃ¨re

-0.13

ientes

-0.13

erd

-0.13

POSITIVE LOGITS

 falls

0.87

 fall

0.86

 falling

0.77

 FALL

0.74

fall

0.73

 Fall

0.71

falls

0.70

Fall

0.68

 Falls

0.66

 fallen

0.66

Activations Density 0.340%

terms related to categorization and definition

No Comments

No Known Activations