INDEX

Explanations

references to space exploration and technology-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ideographic

-0.16

.scalablytyped

-0.16

igr

-0.15

 cáº£

-0.14

:maj

-0.13

 Incontri

-0.13

 Svens

-0.13

èªī

-0.13

Kak

-0.13

 addCriterion

-0.13

POSITIVE LOGITS

 news

0.19

featured

0.18

 Featured

0.17

 featured

0.17

 Feature

0.16

 Slider

0.16

asm

0.15

feature

0.15

Featured

0.15

eature

0.14

Activations Density 0.135%

references to space exploration and technology-related terms

No Comments

No Known Activations