INDEX

Explanations

references to financial terms or wealth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

èĩº

-0.15

eref

-0.14

bove

-0.14

Ð°Ð´ÐºÐ¸

-0.14

ekil

-0.14

ortal

-0.14

urum

-0.14

ãģĹãĤĩãģĨ

-0.14

ittel

-0.14

POSITIVE LOGITS

Ace

0.18

Ace

0.17

 unspecified

0.17

jak

0.16

arya

0.15

jab

0.14

 implication

0.14

ï¼į

0.14

.Highlight

0.14

sert

0.13

Activations Density 0.000%

references to financial terms or wealth

No Comments

No Known Activations