INDEX

Explanations

references to holidays and related events

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

ched

-0.21

ï¸ı

-0.17

/he

-0.17

ray

-0.17

iedad

-0.16

ching

-0.16

ERGE

-0.15

 highly

-0.15

ii

-0.15

hei

-0.15

POSITIVE LOGITS

makers

0.25

maker

0.21

-makers

0.20

-maker

0.18

 makers

0.18

 season

0.17

$MESS

0.16

DITION

0.16

 maker

0.16

Inn

0.16

Activations Density 0.009%

references to holidays and related events

No Comments

No Known Activations