INDEX

Explanations

mathematical expressions and symbols, particularly in the context of equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ortex

-0.14

 ÙĪØ¬Ùĩ

-0.14

rella

-0.14

omo

-0.14

 lucr

-0.14

ieu

-0.14

çĽ

-0.13

 Äĳiá»ĥn

-0.13

opp

-0.13

OutOfBoundsException

-0.13

POSITIVE LOGITS

ãĥªãĤ«

0.15

 Lambert

0.15

.scalablytyped

0.15

oky

0.14

azen

0.14

 Agencies

0.14

yne

0.13

Ð¾ÑĤÐ¾

0.13

 agency

0.13

ay

0.13

Activations Density 0.274%

mathematical expressions and symbols, particularly in the context of equations

No Comments

No Known Activations