INDEX

Explanations

phrases indicating extended durations or longtime associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Tam

-0.15

 IsNot

-0.14

 mitochond

-0.14

oup

-0.14

enti

-0.14

eldom

-0.14

omp

-0.14

è¡£

-0.14

 Mitch

-0.14

Tam

-0.14

POSITIVE LOGITS

arket

0.15

reet

0.14

resar

0.14

 ÅĻÃŃ

0.14

ORTH

0.13

industry

0.13

read

0.13

é«ĺéĢŁ

0.13

osed

0.13

allet

0.13

Activations Density 0.004%

phrases indicating extended durations or longtime associations

No Comments

No Known Activations