INDEX

Explanations

references to the term "Titans."

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

vais

-0.18

ULONG

-0.15

 Ú¯ÙĪ

-0.14

LOUD

-0.14

liv

-0.14

 thÆ°Æ¡ng

-0.13

burgh

-0.13

 skill

-0.13

.UnitTesting

-0.13

POSITIVE LOGITS

Ð¾ÑĢÐ°Ð·

0.15

kola

0.15

ozor

0.14

 Crosby

0.14

urate

0.14

chants

0.13

ebi

0.13

 sings

0.13

 Direct

0.13

pud

0.13

Activations Density 0.000%

references to the term "Titans."

No Comments

No Known Activations