INDEX

Explanations

programming concepts related to function usage and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÏĥÎ±

-0.15

Ø§ÙĪØ±

-0.15

ns

-0.14

ç²Ĺ

-0.14

cae

-0.14

.EventQueue

-0.14

 congest

-0.14

lap

-0.14

/li

-0.13

ÙģØ±

-0.13

POSITIVE LOGITS

dere

0.16

ednou

0.16

_Lean

0.16

 declaraciÃ³n

0.15

å¼ı

0.15

Lam

0.15

ìĭĿ

0.15

nett

0.15

 assignment

0.14

 lamb

0.14

Activations Density 0.093%

programming concepts related to function usage and syntax

No Comments

No Known Activations