INDEX

Explanations

code-related syntax and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

yi

-0.16

_void

-0.16

FileVersion

-0.15

IDL

-0.15

OrFail

-0.15

NotificationCenter

-0.15

TestCategory

-0.14

CommandEvent

-0.14

vecs

-0.14

EMPL

-0.14

POSITIVE LOGITS

 context

0.32

 describe

0.28

context

0.25

 Describe

0.24

Describe

0.23

 Context

0.22

 contexts

0.22

.context

0.22

describe

0.22

(context

0.21

Activations Density 0.010%

code-related syntax and structures

No Comments

No Known Activations