INDEX

Explanations

occurrences of verbs and actions related to sales and transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-away

-0.19

away

-0.17

bak

-0.16

ä¸ĭæĿ¥

-0.16

Away

-0.16

ocop

-0.16

æłª

-0.16

alat

-0.15

 Away

-0.15

oven

-0.15

POSITIVE LOGITS

our

0.18

put

0.16

 inher

0.15

ou

0.15

arda

0.15

 Angiospermae

0.15

avar

0.14

arga

0.14

our

0.14

Activations Density 0.085%

occurrences of verbs and actions related to sales and transactions

No Comments

No Known Activations