INDEX

Explanations

programming-related syntax and structure for defining object properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Longitude

-0.16

sah

-0.16

ourg

-0.15

æł¹

-0.15

estre

-0.15

arias

-0.15

ulum

-0.14

atomic

-0.14

 dwarf

-0.14

arov

-0.13

POSITIVE LOGITS

 tuple

0.24

tuple

0.23

 Tuple

0.21

:CGPoint

0.20

Tuple

0.20

(tuple

0.20

 tuples

0.19

ENU

0.19

_tuple

0.18

 ImVec

0.18

Activations Density 0.140%

programming-related syntax and structure for defining object properties

No Comments

No Known Activations