INDEX

Explanations

programming function calls related to data types and reading operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

atura

-0.15

itr

-0.15

olum

-0.15

 èĩ

-0.15

ocl

-0.14

 NDEBUG

-0.14

 Passenger

-0.14

Kas

-0.14

POSITIVE LOGITS

 string

0.20

 boolean

0.20

 date

0.19

 Boolean

0.18

 complex

0.18

_Bool

0.18

 double

0.18

 bool

0.18

date

0.18

æĹ¥æľŁ

0.18

Activations Density 0.154%

programming function calls related to data types and reading operations

No Comments

No Known Activations