INDEX

Explanations

technical or programming concepts related to functions and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rios

-0.16

venta

-0.15

ATCH

-0.15

astle

-0.15

 Gross

-0.14

 Mach

-0.14

ares

-0.14

ssel

-0.14

ĵĺ

-0.14

sla

-0.14

POSITIVE LOGITS

ials

0.17

ÑĨÐ°

0.16

 Differential

0.15

ayi

0.15

ipl

0.14

ession

0.14

.twitch

0.14

izzazione

0.14

idl

0.14

ox

0.14

Activations Density 0.122%

technical or programming concepts related to functions and methods

No Comments

No Known Activations