INDEX

Explanations

references to various television series and their actors or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

},{↵

-0.17

Ð°ÑĢÐ¾Ð´

-0.15

ickness

-0.15

Ð³Ð»

-0.15

inous

-0.14

 Rowling

-0.14

alloween

-0.14

 McCart

-0.14

apot

-0.13

Ð½Ð°Ð´

-0.13

POSITIVE LOGITS

CSI

0.18

 Agents

0.17

 flash

0.17

CSI

0.17

Ŀi

0.15

 Flash

0.15

 Masters

0.15

0.14

 newPosition

0.14

 pilots

0.14

Activations Density 0.135%

references to various television series and their actors or characters

No Comments

No Known Activations