INDEX

Explanations

references to series of events or consequences in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 depart

-0.16

 Depart

-0.16

quette

-0.15

Pai

-0.15

 Petro

-0.15

ierz

-0.15

iac

-0.15

Dro

-0.14

iem

-0.14

Cle

-0.14

POSITIVE LOGITS

ustr

0.18

axon

0.16

íĻľ

0.15

ãĥķãĤ

0.15

poi

0.14

BorderStyle

0.14

vents

0.14

WithContext

0.14

conciliation

0.14

 ÎĳÎ½

0.14

Activations Density 0.922%

references to series of events or consequences in a narrative

No Comments

No Known Activations