INDEX

Explanations

mentions of "pan" and its derivatives, indicating a focus on related concepts or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ingly

-0.20

ennes

-0.17

emente

-0.15

heet

-0.14

ej

-0.14

 Huffman

-0.14

ulers

-0.14

reh

-0.14

sb

-0.14

sis

-0.14

POSITIVE LOGITS

theon

0.30

asonic

0.28

orama

0.26

zer

0.24

acea

0.24

optic

0.23

ache

0.22

thers

0.22

icked

0.21

handlers

0.20

Activations Density 0.018%

mentions of "pan" and its derivatives, indicating a focus on related concepts or themes

No Comments

No Known Activations