INDEX

Explanations

occurrences of the word "words" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eway

-0.17

åĩ¡

-0.16

(klass

-0.14

eza

-0.14

ogue

-0.14

inois

-0.14

ubit

-0.13

Ra

-0.13

 NavParams

-0.13

alli

-0.13

POSITIVE LOGITS

mith

0.16

.gravity

0.15

/terms

0.15

heimer

0.15

.word

0.15

 trap

0.15

-word

0.14

ight

0.14

/th

0.14

 Äĳáº¿

0.14

Activations Density 0.033%

occurrences of the word "words" and its variations in different contexts

No Comments

No Known Activations