INDEX

Explanations

references to historical figures and etymology

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

ordon

-0.17

 Sentence

-0.15

athe

-0.15

at

-0.15

Sentence

-0.15

 sentences

-0.15

 Grammar

-0.15

 public

-0.14

 implied

-0.14

POSITIVE LOGITS

_NAMES

0.18

 yazÄ±lÄ±

0.17

 names

0.16

istrovstvÃŃ

0.16

REFERRED

0.16

ROLLER

0.16

ĵåĲį

0.16

å§ĵåĲį

0.15

 uÅ¾ÃŃ

0.15

-names

0.15

Activations Density 0.138%

references to historical figures and etymology

No Comments

No Known Activations