INDEX

Explanations

mentions of "Cedar" or "cedar" 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.18

-0.17

 expend

-0.15

¼

-0.15

Hum

-0.15

adf

-0.15

akte

-0.15

osit

-0.14

orb

-0.14

POSITIVE LOGITS

 Rapids

0.18

illos

0.17

holm

0.17

 DÃ¼n

0.16

oldem

0.16

çģ°

0.16

udeau

0.15

vale

0.15

idlo

0.15

velt

0.15

Activations Density 0.005%

mentions of "Cedar" or "cedar" in various contexts

No Comments

No Known Activations