INDEX

Explanations

the word "hopper" and its variations 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abe

-0.17

ury

-0.16

io

-0.15

 consequ

-0.15

ne

-0.15

uc

-0.15

asion

-0.15

ħį

-0.14

 successive

-0.14

 anti

-0.14

POSITIVE LOGITS

arov

0.16

ovatel

0.16

ÏĨÎ¹

0.16

datatable

0.16

iÃª

0.15

-widget

0.15

ãĥĥãĥĦ

0.15

ë¡ľëĵľ

0.15

WithData

0.15

çļ®

0.15

Activations Density 0.005%

the word "hopper" and its variations in various contexts

No Comments

No Known Activations