INDEX

Explanations

phrases indicating the evaluation of conditions or scenarios and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

kyt

-0.16

anche

-0.15

erable

-0.15

RSA

-0.15

ayd

-0.14

kud

-0.14

oine

-0.14

adele

-0.14

¢åįķ

-0.14

inkel

-0.14

POSITIVE LOGITS

 then

0.60

then

0.53

 thÃ¬

0.46

 entonces

0.44

 THEN

0.43

 Then

0.43

Then

0.41

 entÃ£o

0.40

çļĦè¯Ŀ

0.39

THEN

0.39

Activations Density 0.180%

phrases indicating the evaluation of conditions or scenarios and their consequences

No Comments

No Known Activations