INDEX

Explanations

programming-related keywords and identifiers used in function definitions and object methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Mayer

-0.16

ansa

-0.16

kir

-0.15

ocom

-0.15

 Drum

-0.14

en

-0.14

_CALLBACK

-0.14

 Philips

-0.14

aps

-0.14

POSITIVE LOGITS

SENT

0.15

itect

0.15

agar

0.14

à¤Ĥà¤¯

0.14

ninger

0.14

Advertisements

0.14

unker

0.14

ÑĤÐ¸

0.14

rought

0.14

Activations Density 0.005%

programming-related keywords and identifiers used in function definitions and object methods

No Comments

No Known Activations