INDEX

Explanations

references to people and entities in a relational context

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

enso

-0.15

-0.14

cks

-0.14

Ð¾Ð²Ð°Ð½Ð¸

-0.14

-0.13

ikh

-0.13

Ø§Ø°

-0.13

 SÃ¼r

-0.13

POSITIVE LOGITS

ARRANT

0.19

skyt

0.17

ãĤ¿ãĥ³

0.15

lemen

0.14

à¸¸à¹ī

0.14

swick

0.14

SGlobal

0.14

rog

0.14

DTD

0.14

ÎķÎ¥

0.14

Activations Density 0.776%

references to people and entities in a relational context

No Comments

No Known Activations