INDEX

Explanations

discussions about analysis and examination of topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ð¾Ð»Ð¾Ñģ

-0.16

 Hairst

-0.15

ucer

-0.15

orman

-0.15

ilet

-0.15

mos

-0.15

raud

-0.14

-caret

-0.14

ilim

-0.14

Ð¾ÑģÐ¿

-0.14

POSITIVE LOGITS

ller

0.16

usi

0.15

aman

0.15

voie

0.15

voje

0.14

symbols

0.14

HLT

0.14

itere

0.14

UTTON

0.14

tol

0.13

Activations Density 0.097%

discussions about analysis and examination of topics

No Comments

No Known Activations