INDEX

Explanations

terms related to analysis and interpretation of data, especially in a financial context

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

xCD

-0.15

_globals

-0.15

awai

-0.15

ilater

-0.15

_WAKE

-0.14

ValidationError

-0.14

ifen

-0.14

oller

-0.14

akin

-0.14

POSITIVE LOGITS

oit

0.15

che

0.15

iminal

0.15

æĪĺ

0.15

 createAction

0.15

porte

0.15

icious

0.15

lendi

0.14

 trem

0.14

_fraction

0.14

Activations Density 0.012%

terms related to analysis and interpretation of data, especially in a financial context

No Comments

No Known Activations