INDEX

Explanations

terms related to triggering emotions or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

imony

-0.15

CompleteListener

-0.15

 seedu

-0.14

DeltaTime

-0.14

 absence

-0.14

ishment

-0.14

fter

-0.14

reau

-0.14

asper

-0.14

enance

-0.14

POSITIVE LOGITS

 dormant

0.27

 debate

0.24

 interest

0.23

 responses

0.21

 response

0.20

 interesse

0.20

 debates

0.20

 chain

0.20

 reactions

0.19

 latent

0.18

Activations Density 0.092%

terms related to triggering emotions or actions

No Comments

No Known Activations