INDEX

Explanations

comparisons involving quantities or amounts, particularly those related to less-than or more-than thresholds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

vla

-0.16

ctl

-0.15

 bang

-0.15

gress

-0.15

edes

-0.14

 DateTimeKind

-0.14

ä¹ħ

-0.14

amedi

-0.14

setError

-0.14

yster

-0.13

POSITIVE LOGITS

(<

0.23

ovsky

0.17

 circ

0.15

sb

0.15

 circumstances

0.15

halb

0.14

Ð²Ð¸Ð¶

0.14

lings

0.14

ack

0.14

lor

0.14

Activations Density 0.098%

comparisons involving quantities or amounts, particularly those related to less-than or more-than thresholds

No Comments

No Known Activations