INDEX

Explanations

occurrences of the verb "to be" in various tenses and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Pand

-0.17

mall

-0.16

ILD

-0.15

Mocks

-0.15

isia

-0.15

ubi

-0.14

ad

-0.14

 Paren

-0.14

 Presenter

-0.13

POSITIVE LOGITS

aroo

0.16

oom

0.16

eview

0.16

ekli

0.14

aylor

0.14

 neutral

0.14

resco

0.14

 permanent

0.14

/mod

0.14

stu

0.14

Activations Density 0.001%

occurrences of the verb "to be" in various tenses and contexts

No Comments

No Known Activations