INDEX

Explanations

words and phrases related to entities and their attributes, particularly in the context of descriptions and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

usch

-0.17

rrha

-0.15

æĭħ

-0.14

igkeit

-0.14

_Interface

-0.14

alian

-0.14

 Hutchinson

-0.14

POSITIVE LOGITS

ìħ

0.15

GenericType

0.15

ÑįÐ¹

0.15

ãĤ·ãĥ§ãĥ³

0.14

ÏĥÎ¹Î¼Î¿

0.14

GT

0.13

Ð¾Ñĩ

0.13

ÑĭÐ¹

0.13

agraph

0.13

share

0.13

Activations Density 0.162%

words and phrases related to entities and their attributes, particularly in the context of descriptions and evaluations

No Comments

No Known Activations