INDEX

Explanations

numerical data, specifically years and identifiers leading to statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

atorium

-0.15

inki

-0.15

 PartialView

-0.15

hei

-0.15

arest

-0.15

lia

-0.14

stown

-0.14

nesia

-0.14

chia

-0.14

ouz

-0.14

POSITIVE LOGITS

istring

0.16

Ð½Ð¸ÑĤ

0.15

OL

0.15

cof

0.14

Rag

0.14

 Ellis

0.14

DetailsService

0.14

 Exec

0.14

ØªØ±ÙĦ

0.13

plit

0.13

Activations Density 0.047%

numerical data, specifically years and identifiers leading to statistical information

No Comments

No Known Activations