INDEX

Explanations

instances of the term "Escalation" or its variants in the context of escalating situations or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

kening

-0.16

ety

-0.16

ifdef

-0.15

ouden

-0.15

atis

-0.15

ings

-0.15

ernals

-0.14

ebb

-0.14

edImage

-0.14

esty

-0.14

POSITIVE LOGITS

uela

0.28

apist

0.27

aping

0.27

APE

0.25

obar

0.24

esc

0.23

rito

0.23

apes

0.23

row

0.23

ambia

0.23

Activations Density 0.006%

instances of the term "Escalation" or its variants in the context of escalating situations or events

No Comments

No Known Activations