INDEX

Explanations

specific terms related to technology, especially smartphones and their features, as well as elements denoting categorization and specialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ivec

-0.16

 Eins

-0.15

vo

-0.14

uish

-0.14

Dog

-0.14

pear

-0.14

jar

-0.14

 round

-0.14

round

-0.14

-round

-0.13

POSITIVE LOGITS

_Variable

0.17

uem

0.15

ero

0.15

Ð°ÑĢÑħ

0.14

Ã¼cken

0.14

 Plate

0.14

ä

0.14

uguay

0.14

hy

0.14

Hy

0.14

Activations Density 0.239%

specific terms related to technology, especially smartphones and their features, as well as elements denoting categorization and specialization

No Comments

No Known Activations