INDEX

Explanations

repetitive phrases and calls to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ufac

-0.15

.idea

-0.14

ucid

-0.14

æİĪ

-0.14

prit

-0.14

uito

-0.14

antis

-0.14

 Pearce

-0.14

ampion

-0.13

ntag

-0.13

POSITIVE LOGITS

ernen

0.17

/Edit

0.15

 donc

0.14

OID

0.14

 Fucking

0.14

vens

0.13

ÑĢÑı

0.13

Å¼

0.13

DBC

0.13

Activations Density 0.153%

repetitive phrases and calls to action

No Comments

No Known Activations