INDEX

Explanations

mathematical symbols and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ts

-0.15

alat

-0.15

ovÃ¡

-0.15

æľį

-0.14

ãĥ³ãĥĦ

-0.14

dden

-0.14

afi

-0.14

å·

-0.14

_TestCase

-0.14

anyak

-0.14

POSITIVE LOGITS

[++

0.19

ulus

0.19

orus

0.16

 Ð·Ð°Ð²ÑĤÑĢÐ°

0.15

umper

0.15

obuf

0.14

Ep

0.14

ë¶Ī

0.14

 Gould

0.14

orrow

0.14

Activations Density 0.079%

mathematical symbols and expressions

No Comments

No Known Activations