INDEX

Explanations

specific numerical and coding references related to document or data structures

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

 Ellen

-0.15

yer

-0.15

Ð¾Ð»Ð¾Ñģ

-0.14

 frac

-0.14

 hypers

-0.14

 Gateway

-0.14

osi

-0.14

 girl

-0.13

simp

-0.13

POSITIVE LOGITS

roje

0.17

utenberg

0.17

ÅĻes

0.15

ilot

0.15

uron

0.15

orte

0.15

usra

0.15

arma

0.14

obili

0.14

utura

0.14

Activations Density 0.013%

specific numerical and coding references related to document or data structures

No Comments

No Known Activations