INDEX

Explanations

export statements in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ħ§

-0.14

_dropout

-0.14

_construct

-0.14

 immobil

-0.13

gnore

-0.13

wis

-0.13

VOID

-0.13

 miÃªu

-0.13

uk

-0.13

iba

-0.13

POSITIVE LOGITS

 default

0.38

 const

0.37

 function

0.34

 interface

0.32

 enum

0.29

default

0.29

 class

0.28

let

0.28

 namespace

0.27

 declare

0.27

Activations Density 0.003%

export statements in the code

No Comments

No Known Activations