INDEX

Explanations

articles preceding nouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

arge

-0.16

dom

-0.14

il

-0.14

nel

-0.14

eral

-0.14

raj

-0.13

 reveal

-0.13

ãĤ¿ãĥ«

-0.13

ICT

-0.13

POSITIVE LOGITS

.gdx

0.16

nbr

0.15

ipsis

0.15

ÙĴØ¹

0.14

è¬

0.14

.twimg

0.14

iser

0.14

æł·

0.14

anio

0.14

 ÄĳÃ£i

0.14

Activations Density 0.055%

articles preceding nouns

No Comments

No Known Activations