INDEX

Explanations

references to dates and years, particularly in financial or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tach

-0.15

 Rolls

-0.14

ands

-0.14

rÃ¡

-0.14

 backward

-0.14

tÃŃ

-0.13

 McKenzie

-0.13

 kÃ¥

-0.13

Ã¡f

-0.13

itzer

-0.13

POSITIVE LOGITS

unday

0.21

idden

0.18

 Aires

0.16

ogui

0.15

ëį°

0.15

prite

0.15

ksam

0.14

 Morrison

0.14

 isize

0.14

uales

0.14

Activations Density 0.069%

references to dates and years, particularly in financial or legal contexts

No Comments

No Known Activations