INDEX

Explanations

references to Python and its related programming components

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

 traces

-0.15

posta

-0.15

legen

-0.14

ames

-0.14

 Jonas

-0.14

ncia

-0.14

slash

-0.14

ignKey

-0.14

liers

-0.14

 Gent

-0.13

POSITIVE LOGITS

atri

0.16

ilden

0.15

_launch

0.15

xs

0.15

zell

0.15

elmet

0.15

udget

0.15

:async

0.15

Äįel

0.14

 trainable

0.14

Activations Density 0.023%

references to Python and its related programming components

No Comments

No Known Activations