INDEX

Explanations

key terms related to reasoning and justification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Has

-0.17

isko

-0.15

Has

-0.15

zh

-0.14

iso

-0.14

Makes

-0.14

-has

-0.14

ISO

-0.14

HAS

-0.14

Provides

-0.13

POSITIVE LOGITS

is

0.56

çļĦæĺ¯

0.51

 adalah

0.40

å°±æĺ¯

0.34

are

0.33

 æĺ¯

0.32

ãģ®ãģ¯

0.31

æĺ¯åľ¨

0.31

was

0.30

 lÃł

0.30

Activations Density 0.491%

key terms related to reasoning and justification in various contexts

No Comments

No Known Activations