INDEX

Explanations

common actions involving giving or taking items in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

isan

-0.16

pyl

-0.15

 Paren

-0.14

 furniture

-0.14

itom

-0.14

imon

-0.14

 chests

-0.14

rint

-0.14

 pods

-0.14

bserv

-0.14

POSITIVE LOGITS

 folder

0.20

 calculator

0.18

 Folder

0.17

 collaps

0.17

 bible

0.17

 Bible

0.17

 packet

0.17

 CreateMap

0.17

 atlas

0.16

 copy

0.16

Activations Density 0.380%

common actions involving giving or taking items in a narrative context

No Comments

No Known Activations