INDEX

Explanations

grammatical terms and classifications, particularly focusing on verbs and adjectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/Dk

-0.17

ONGL

-0.17

antz

-0.17

kÃ¼n

-0.16

.getColumnModel

-0.16

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

-0.15

Ã¡nt

-0.14

tura

-0.14

.nlm

-0.14

 Gould

-0.14

POSITIVE LOGITS

ripe

0.15

endon

0.14

 Interviews

0.14

het

0.14

ivalence

0.14

icut

0.14

arto

0.14

 cloned

0.14

 House

0.14

Activations Density 0.073%

grammatical terms and classifications, particularly focusing on verbs and adjectives

No Comments

No Known Activations