INDEX

Explanations

mentions of the word "Strath" and its variations in context

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

incinn

-0.17

Ã§ek

-0.16

 CHtml

-0.16

ieres

-0.16

iali

-0.15

ikat

-0.15

.Exit

-0.15

annot

-0.15

eel

-0.14

isoft

-0.14

POSITIVE LOGITS

ses

0.16

ematic

0.16

ais

0.15

Ð°Ð½Ð¸ÑĨ

0.15

ore

0.15

esis

0.14

ttp

0.14

ur

0.14

ym

0.14

Activations Density 0.023%

mentions of the word "Strath" and its variations in context

No Comments

No Known Activations