INDEX

Explanations

instances of the word "actually" and related terms indicating reality or authenticity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

erge

-0.15

tips

-0.15

esh

-0.15

ÐµÑĪ

-0.15

quat

-0.15

kle

-0.15

 Minerals

-0.14

osal

-0.14

tre

-0.14

_SOL

-0.14

POSITIVE LOGITS

iano

0.17

 Gron

0.16

anking

0.15

Ung

0.14

WithContext

0.14

oire

0.14

Ø²Ø§Ùħ

0.14

owell

0.14

kenin

0.14

/false

0.14

Activations Density 0.036%

instances of the word "actually" and related terms indicating reality or authenticity

No Comments

No Known Activations