INDEX

Explanations

references to personal or possessive pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 vault

-0.17

(es

-0.16

iaux

-0.15

esus

-0.15

ials

-0.14

abled

-0.14

ibli

-0.14

 Vault

-0.14

 skipping

-0.14

(s

-0.13

POSITIVE LOGITS

 presenter

0.19

 present

0.17

present

0.17

_CHAN

0.17

 presentation

0.16

 presenting

0.16

 Treat

0.15

 Present

0.15

 prÃ©sent

0.15

Present

0.15

Activations Density 0.023%

references to personal or possessive pronouns

No Comments

No Known Activations